Guillermo Gallego
Photo: SCIoI
Guillermo Gallego is Professor of Robotic Interactive Perception at Technische Universität Berlin and Einstein Center Digital Future (ECDF). For SCIoI, he works on computer vision and robotics. He focuses on robot perception and on optimization methods for interdisciplinary imaging and control problems. Inspired by the human visual system, he works toward improving the perception systems of artificial agents, endowing them with intelligence to transform raw sensor data into knowledge, to provide autonomy in changing environments.
Projects
Guillermo Gallego is member of:
Publications +
6984777
Gallego
1
apa
50
date
desc
year
19851
https://www.scienceofintelligence.de/wp-content/plugins/zotpress/
%7B%22status%22%3A%22success%22%2C%22updateneeded%22%3Afalse%2C%22instance%22%3Afalse%2C%22meta%22%3A%7B%22request_last%22%3A0%2C%22request_next%22%3A0%2C%22used_cache%22%3Atrue%7D%2C%22data%22%3A%5B%7B%22key%22%3A%22XGAMLRJ2%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Guo%20et%20al.%22%2C%22parsedDate%22%3A%222026-03-15%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGuo%2C%20S.%2C%20Febryanto%2C%20F.%2C%20Sun%2C%20L.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282026%29.%20%26lt%3Bi%26gt%3BInterp3R%3A%20Continuous-time%203D%20Geometry%20Estimation%20with%20Frames%20and%20Events%26lt%3B%5C%2Fi%26gt%3B%20%28arXiv%3A2603.14528%29.%20arXiv.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2603.14528%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.48550%5C%2FarXiv.2603.14528%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22preprint%22%2C%22title%22%3A%22Interp3R%3A%20Continuous-time%203D%20Geometry%20Estimation%20with%20Frames%20and%20Events%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shuang%22%2C%22lastName%22%3A%22Guo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Filbert%22%2C%22lastName%22%3A%22Febryanto%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lei%22%2C%22lastName%22%3A%22Sun%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22In%20recent%20years%2C%203D%20visual%20foundation%20models%20pioneered%20by%20pointmap-based%20approaches%20such%20as%20DUSt3R%20have%20attracted%20a%20lot%20of%20interest%2C%20achieving%20impressive%20accuracy%20and%20strong%20generalization%20across%20diverse%20scenes.%20However%2C%20these%20methods%20are%20inherently%20limited%20to%20recovering%20scene%20geometry%20only%20at%20the%20discrete%20time%20instants%20when%20images%20are%20captured%2C%20leaving%20the%20scene%20evolution%20during%20the%20blind%20time%20between%20consecutive%20frames%20largely%20unexplored.%20We%20introduce%20Interp3R%2C%20to%20the%20best%20of%20our%20knowledge%20the%20first%20method%20that%20enhances%20pointmap-based%20models%20to%20estimate%20depth%20and%20camera%20poses%20at%20arbitrary%20time%20instants.%20Interp3R%20leverages%20asynchronous%20event%20data%20to%20interpolate%20pointmaps%20produced%20by%20frame-based%20models%2C%20enabling%20temporally%20continuous%20geometric%20representations.%20Depth%20and%20camera%20poses%20are%20then%20jointly%20recovered%20by%20aligning%20the%20interpolated%20pointmaps%20together%20with%20those%20predicted%20by%20the%20underlying%20frame-based%20models%20into%20a%20consistent%20spatial%20framework.%20We%20train%20Interp3R%20exclusively%20on%20a%20synthetic%20dataset%2C%20yet%20demonstrate%20strong%20generalization%20across%20a%20wide%20range%20of%20synthetic%20and%20real-world%20benchmarks.%20Extensive%20experiments%20show%20that%20Interp3R%20outperforms%20by%20a%20considerable%20margin%20state-of-the-art%20baselines%20that%20follow%20a%20two-stage%20pipeline%20of%202D%20video%20frame%20interpolation%20followed%20by%203D%20geometry%20estimation.%22%2C%22genre%22%3A%22%22%2C%22repository%22%3A%22arXiv%22%2C%22archiveID%22%3A%22arXiv%3A2603.14528%22%2C%22date%22%3A%222026-03-15%22%2C%22DOI%22%3A%2210.48550%5C%2FarXiv.2603.14528%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22http%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2603.14528%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T12%3A05%3A02Z%22%7D%7D%2C%7B%22key%22%3A%226GEQA27A%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Bartolomei%20et%20al.%22%2C%22parsedDate%22%3A%222026%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BBartolomei%2C%20L.%2C%20Tosi%2C%20F.%2C%20Poggi%2C%20M.%2C%20Mattoccia%2C%20S.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282026%29.%20%26lt%3Bi%26gt%3BEventHub%3A%20Data%20Factory%20for%20Generalizable%20Event-Based%20Stereo%20Networks%20without%20Active%20Sensors%26lt%3B%5C%2Fi%26gt%3B.%20IEEE%5C%2FCVF%20Computer%20Vision%20and%20Pattern%20Recognition%20Conference%20%28CVPR%29.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fbartn8.github.io%5C%2Feventhub%5C%2F%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fbartn8.github.io%5C%2Feventhub%5C%2F%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22EventHub%3A%20Data%20Factory%20for%20Generalizable%20Event-Based%20Stereo%20Networks%20without%20Active%20Sensors%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Luca%22%2C%22lastName%22%3A%22Bartolomei%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabio%22%2C%22lastName%22%3A%22Tosi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Matteo%22%2C%22lastName%22%3A%22Poggi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Stefano%22%2C%22lastName%22%3A%22Mattoccia%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22proceedingsTitle%22%3A%22%22%2C%22conferenceName%22%3A%22IEEE%5C%2FCVF%20Computer%20Vision%20and%20Pattern%20Recognition%20Conference%20%28CVPR%29%22%2C%22date%22%3A%222026%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%22%22%2C%22ISBN%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fbartn8.github.io%5C%2Feventhub%5C%2F%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-26T09%3A30%3A36Z%22%7D%7D%2C%7B%22key%22%3A%22LU2PXDX4%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Kohyama%20et%20al.%22%2C%22parsedDate%22%3A%222026%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BKohyama%2C%20K.%2C%20Aoki%2C%20Y.%2C%20Gallego%2C%20G.%2C%20%26amp%3B%20Shiba%2C%20S.%20%282026%29.%20%26lt%3Bi%26gt%3BGeometric-Photometric%20Event-based%203D%20Gaussian%20Ray%20Tracing%26lt%3B%5C%2Fi%26gt%3B.%20IEEE%5C%2FCVF%20Computer%20Vision%20and%20Pattern%20Recognition%20Conference%20%28CVPR%29.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fe3ai.github.io%5C%2Fgpert%5C%2F%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fe3ai.github.io%5C%2Fgpert%5C%2F%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Geometric-Photometric%20Event-based%203D%20Gaussian%20Ray%20Tracing%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kai%22%2C%22lastName%22%3A%22Kohyama%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yoshimitsu%22%2C%22lastName%22%3A%22Aoki%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shintaro%22%2C%22lastName%22%3A%22Shiba%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22proceedingsTitle%22%3A%22%22%2C%22conferenceName%22%3A%22IEEE%5C%2FCVF%20Computer%20Vision%20and%20Pattern%20Recognition%20Conference%20%28CVPR%29%22%2C%22date%22%3A%222026%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%22%22%2C%22ISBN%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fe3ai.github.io%5C%2Fgpert%5C%2F%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-26T09%3A27%3A23Z%22%7D%7D%2C%7B%22key%22%3A%22JZ4JZGQK%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Gallego%20et%20al.%22%2C%22parsedDate%22%3A%222026%22%2C%22numChildren%22%3A0%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGallego%2C%20G.%2C%20Hidalgo-Carri%26%23xF3%3B%2C%20J.%2C%20%26amp%3B%20Scaramuzza%2C%20D.%20%282026%29.%20Event-based%20SLAM.%20In%20L.%20Carlone%2C%20A.%20Kim%2C%20T.%20Barfoot%2C%20D.%20Cremers%2C%20%26amp%3B%20F.%20Dellaert%20%28Eds.%29%2C%20%26lt%3Bi%26gt%3BSLAM%20Handbook.%20From%20Localization%20and%20Mapping%20to%20Spatial%20Intelligence%26lt%3B%5C%2Fi%26gt%3B.%20Cambridge%20University%20Press.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fgithub.com%5C%2FSLAM-Handbook-contributors%5C%2Fslam-handbook-public-release%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fgithub.com%5C%2FSLAM-Handbook-contributors%5C%2Fslam-handbook-public-release%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22bookSection%22%2C%22title%22%3A%22Event-based%20SLAM%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Javier%22%2C%22lastName%22%3A%22Hidalgo-Carri%5Cu00f3%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Davide%22%2C%22lastName%22%3A%22Scaramuzza%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Luca%22%2C%22lastName%22%3A%22Carlone%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Ayoung%22%2C%22lastName%22%3A%22Kim%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Timothy%22%2C%22lastName%22%3A%22Barfoot%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Daniel%22%2C%22lastName%22%3A%22Cremers%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Frank%22%2C%22lastName%22%3A%22Dellaert%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22bookTitle%22%3A%22SLAM%20Handbook.%20From%20Localization%20and%20Mapping%20to%20Spatial%20Intelligence%22%2C%22date%22%3A%222026%22%2C%22originalDate%22%3A%22%22%2C%22originalPublisher%22%3A%22%22%2C%22originalPlace%22%3A%22%22%2C%22format%22%3A%22%22%2C%22ISBN%22%3A%22%22%2C%22DOI%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fgithub.com%5C%2FSLAM-Handbook-contributors%5C%2Fslam-handbook-public-release%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-26T09%3A32%3A35Z%22%7D%7D%2C%7B%22key%22%3A%22KURJK742%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Hitzges%20et%20al.%22%2C%22parsedDate%22%3A%222025-12%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BHitzges%2C%20D.%20de%20O.%2C%20Ghosh%2C%20S.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282025%2C%20December%29.%20%26lt%3Bi%26gt%3BDERD-Net%3A%20Learning%20Depth%20from%20Event-based%20Ray%20Densities%26lt%3B%5C%2Fi%26gt%3B.%2039th%20Annual%20Conference%20on%20Neural%20Information%20Processing%20Systems%20%28NeurIPS%29.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2504.15863%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2504.15863%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22DERD-Net%3A%20Learning%20Depth%20from%20Event-based%20Ray%20Densities%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Diego%20de%20Oliveira%22%2C%22lastName%22%3A%22Hitzges%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Suman%22%2C%22lastName%22%3A%22Ghosh%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22Event%20cameras%20offer%20a%20promising%20avenue%20for%20multi-view%20stereo%20depth%20estimation%20and%20Simultaneous%20Localization%20And%20Mapping%20%28SLAM%29%20due%20to%20their%20ability%20to%20detect%20blur-free%203D%20edges%20at%20high-speed%20and%20over%20broad%20illumination%20conditions.%20However%2C%20traditional%20deep%20learning%20frameworks%20designed%20for%20conventional%20cameras%20struggle%20with%20the%20asynchronous%2C%20stream-like%20nature%20of%20event%20data%2C%20as%20their%20architectures%20are%20optimized%20for%20discrete%2C%20image-like%20inputs.%20We%20propose%20a%20scalable%2C%20flexible%20and%20adaptable%20framework%20for%20pixel-wise%20depth%20estimation%20with%20event%20cameras%20in%20both%20monocular%20and%20stereo%20setups.%20The%203D%20scene%20structure%20is%20encoded%20into%20disparity%20space%20images%20%28DSIs%29%2C%20representing%20spatial%20densities%20of%20rays%20obtained%20by%20back-projecting%20events%20into%20space%20via%20known%20camera%20poses.%20Our%20neural%20network%20processes%20local%20subregions%20of%20the%20DSIs%20combining%203D%20convolutions%20and%20a%20recurrent%20structure%20to%20recognize%20valuable%20patterns%20for%20depth%20prediction.%20Local%20processing%20enables%20fast%20inference%20with%20full%20parallelization%20and%20ensures%20constant%20ultra-low%20model%20complexity%20and%20memory%20costs%2C%20regardless%20of%20camera%20resolution.%20Experiments%20on%20standard%20benchmarks%20%28MVSEC%20and%20DSEC%20datasets%29%20demonstrate%20unprecedented%20effectiveness%3A%20%28i%29%20using%20purely%20monocular%20data%2C%20our%20method%20achieves%20comparable%20results%20to%20existing%20stereo%20methods%3B%20%28ii%29%20when%20applied%20to%20stereo%20data%2C%20it%20strongly%20outperforms%20all%20state-of-the-art%20%28SOTA%29%20approaches%2C%20reducing%20the%20mean%20absolute%20error%20by%20at%20least%2042%5C%5C%25%3B%20%28iii%29%20our%20method%20also%20allows%20for%20increases%20in%20depth%20completeness%20by%20more%20than%203-fold%20while%20still%20yielding%20a%20reduction%20in%20median%20absolute%20error%20of%20at%20least%2030%5C%5C%25.%20Given%20its%20remarkable%20performance%20and%20effective%20processing%20of%20event-data%2C%20our%20framework%20holds%20strong%20potential%20to%20become%20a%20standard%20approach%20for%20using%20deep%20learning%20for%20event-based%20depth%20estimation%20and%20SLAM.%22%2C%22proceedingsTitle%22%3A%22%22%2C%22conferenceName%22%3A%2239th%20Annual%20Conference%20on%20Neural%20Information%20Processing%20Systems%20%28NeurIPS%29%22%2C%22date%22%3A%222025%5C%2F12%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%22%22%2C%22ISBN%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2504.15863%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-26T09%3A37%3A36Z%22%7D%7D%2C%7B%22key%22%3A%22MYBFPA7Q%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Guo%20et%20al.%22%2C%22parsedDate%22%3A%222025-10%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGuo%2C%20S.%2C%20Hamann%2C%20F.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282025%29.%20Unsupervised%20Joint%20Learning%20of%20Optical%20Flow%20and%20Intensity%20with%20Event%20Cameras.%20%26lt%3Bi%26gt%3B2025%20IEEE%5C%2FCVF%20International%20Conference%20on%20Computer%20Vision%20%28ICCV%29%26lt%3B%5C%2Fi%26gt%3B%2C%207980%26%23x2013%3B7989.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FICCV51701.2025.00748%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FICCV51701.2025.00748%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Unsupervised%20Joint%20Learning%20of%20Optical%20Flow%20and%20Intensity%20with%20Event%20Cameras%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shuang%22%2C%22lastName%22%3A%22Guo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Friedhelm%22%2C%22lastName%22%3A%22Hamann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22Event%20cameras%20rely%20on%20motion%20to%20obtain%20information%20about%20scene%20appearance.%20This%20means%20that%20appearance%20and%20motion%20are%20inherently%20linked%3A%20either%20both%20are%20present%20and%20recorded%20in%20the%20event%20data%2C%20or%20neither%20is%20captured.%20Previous%20works%20treat%20the%20recovery%20of%20these%20two%20visual%20quantities%20as%20separate%20tasks%2C%20which%20does%20not%20fit%20with%20the%20above-mentioned%20nature%20of%20event%20cameras%20and%20overlooks%20the%20inherent%20relations%20between%20them.%20We%20propose%20an%20unsupervised%20learning%20framework%20that%20jointly%20estimates%20optical%20flow%20%28motion%29%20and%20image%20intensity%20%28appearance%29%20using%20a%20single%20network.%20From%20the%20data%20generation%20model%2C%20we%20newly%20derive%20the%20event-based%20photometric%20error%20as%20a%20function%20of%20optical%20flow%20and%20image%20intensity.%20This%20error%20is%20further%20combined%20with%20the%20contrast%20maximization%20framework%20to%20form%20a%20comprehensive%20loss%20function%20that%20provides%20proper%20constraints%20for%20both%20flow%20and%20intensity%20estimation.%20Exhaustive%20experiments%20show%20our%20method%26%23039%3Bs%20state-of-the-art%20performance%3A%20in%20optical%20flow%20estimation%2C%20it%20reduces%20EPE%20by%2020%25%20and%20A%20E%20by%2025%25%20compared%20to%20unsupervised%20approaches%2C%20while%20delivering%20competitive%20intensity%20estimation%20results%2C%20particularly%20in%20high%20dynamic%20range%20scenarios.%20Our%20method%20also%20achieves%20shorter%20inference%20time%20than%20all%20other%20optical%20flow%20methods%20and%20many%20of%20the%20image%20reconstruction%20methods%2C%20while%20they%20output%20only%20one%20quantity.%20Project%20page%3A%20https%3A%5C%2F%5C%2Fgithub.com%5C%2Ftub-rip%5C%2FE2FAI%22%2C%22proceedingsTitle%22%3A%222025%20IEEE%5C%2FCVF%20International%20Conference%20on%20Computer%20Vision%20%28ICCV%29%22%2C%22conferenceName%22%3A%222025%20IEEE%5C%2FCVF%20International%20Conference%20on%20Computer%20Vision%20%28ICCV%29%22%2C%22date%22%3A%222025-10%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FICCV51701.2025.00748%22%2C%22ISBN%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F11444738%22%2C%22ISSN%22%3A%222380-7504%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A25Z%22%7D%7D%2C%7B%22key%22%3A%22QFNLIJ65%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Hamann%20et%20al.%22%2C%22parsedDate%22%3A%222025-10%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BHamann%2C%20F.%2C%20Mededovic%2C%20E.%2C%20G%26%23xFC%3Blhan%2C%20F.%2C%20Wu%2C%20Y.%2C%20Stegmaier%2C%20J.%2C%20He%2C%20J.%2C%20Wang%2C%20Y.%2C%20Zhang%2C%20K.%2C%20Li%2C%20L.%2C%20Jiao%2C%20L.%2C%20Ma%2C%20M.%2C%20Huang%2C%20H.%2C%20Yan%2C%20Y.%2C%20Ren%2C%20H.%2C%20Lin%2C%20X.%2C%20Huang%2C%20Y.%2C%20Cheng%2C%20B.%2C%20Lee%2C%20S.%20H.%2C%20Ham%2C%20G.%20S.%2C%20%26%23x2026%3B%20Gallego%2C%20G.%20%282025%29.%20SIS-Challenge%3A%20Event-Based%20Spatio-Temporal%20Instance%20Segmentation%20Challenge%20at%20the%20CVPR%202025%20Event-Based%20Vision%20Workshop.%20%26lt%3Bi%26gt%3B2025%20IEEE%5C%2FCVF%20International%20Conference%20on%20Computer%20Vision%20Workshops%20%28ICCVW%29%26lt%3B%5C%2Fi%26gt%3B%2C%204734%26%23x2013%3B4742.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FICCVW69036.2025.00491%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FICCVW69036.2025.00491%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22SIS-Challenge%3A%20Event-Based%20Spatio-Temporal%20Instance%20Segmentation%20Challenge%20at%20the%20CVPR%202025%20Event-Based%20Vision%20Workshop%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Friedhelm%22%2C%22lastName%22%3A%22Hamann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Emil%22%2C%22lastName%22%3A%22Mededovic%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Fabian%22%2C%22lastName%22%3A%22G%5Cu00fclhan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yuli%22%2C%22lastName%22%3A%22Wu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Johannes%22%2C%22lastName%22%3A%22Stegmaier%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jing%22%2C%22lastName%22%3A%22He%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yiqing%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kexin%22%2C%22lastName%22%3A%22Zhang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lingling%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Licheng%22%2C%22lastName%22%3A%22Jiao%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Mengru%22%2C%22lastName%22%3A%22Ma%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hongxiang%22%2C%22lastName%22%3A%22Huang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yuhao%22%2C%22lastName%22%3A%22Yan%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hongwei%22%2C%22lastName%22%3A%22Ren%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xiaopeng%22%2C%22lastName%22%3A%22Lin%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yulong%22%2C%22lastName%22%3A%22Huang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bojun%22%2C%22lastName%22%3A%22Cheng%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Se%20Hyun%22%2C%22lastName%22%3A%22Lee%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gyu%20Sung%22%2C%22lastName%22%3A%22Ham%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kanghan%22%2C%22lastName%22%3A%22Oh%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Gi%20Hyun%22%2C%22lastName%22%3A%22Lim%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Boxuan%22%2C%22lastName%22%3A%22Yang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bowen%22%2C%22lastName%22%3A%22Du%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22We%20present%20an%20overview%20of%20the%20Spatio-temporal%20Instance%20Segmentation%20%28SIS%29%20challenge%20held%20in%20conjunction%20with%20the%20CVPR%202025%20Event-based%20Vision%20Workshop.%20The%20task%20is%20to%20predict%20accurate%20pixel-level%20segmentation%20masks%20of%20defined%20object%20classes%20from%20spatio-temporally%20aligned%20event%20camera%20and%20grayscale%20camera%20data.%20We%20provide%20an%20overview%20of%20the%20task%2C%20dataset%2C%20challenge%20details%20and%20results.%20Furthermore%2C%20we%20describe%20the%20methods%20used%20by%20the%20top-5%20ranking%20teams%20in%20the%20challenge.%20More%20resources%20and%20code%20of%20the%20participants%26%23039%3B%20methods%20are%20available%20here%3A%20https%3A%5C%2F%5C%2Fgithub.com%5C%2Ftubrip%5C%2FMouseSIS%5C%2Fblob%5C%2Fmain%5C%2Fdocs%5C%2Fchallengeesults.md%22%2C%22proceedingsTitle%22%3A%222025%20IEEE%5C%2FCVF%20International%20Conference%20on%20Computer%20Vision%20Workshops%20%28ICCVW%29%22%2C%22conferenceName%22%3A%222025%20IEEE%5C%2FCVF%20International%20Conference%20on%20Computer%20Vision%20Workshops%20%28ICCVW%29%22%2C%22date%22%3A%222025-10%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FICCVW69036.2025.00491%22%2C%22ISBN%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F11374462%22%2C%22ISSN%22%3A%222473-9944%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T12%3A04%3A17Z%22%7D%7D%2C%7B%22key%22%3A%22Y85C8JYG%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Shiba%20et%20al.%22%2C%22parsedDate%22%3A%222025-10%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BShiba%2C%20S.%2C%20Aoki%2C%20Y.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282025%29.%20Simultaneous%20Motion%20and%20Noise%20Estimation%20with%20Event%20Cameras.%20%26lt%3Bi%26gt%3B2025%20IEEE%5C%2FCVF%20International%20Conference%20on%20Computer%20Vision%20%28ICCV%29%26lt%3B%5C%2Fi%26gt%3B%2C%206959%26%23x2013%3B6969.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FICCV51701.2025.00654%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FICCV51701.2025.00654%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Simultaneous%20Motion%20and%20Noise%20Estimation%20with%20Event%20Cameras%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shintaro%22%2C%22lastName%22%3A%22Shiba%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yoshimitsu%22%2C%22lastName%22%3A%22Aoki%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22Event%20cameras%20are%20emerging%20vision%20sensors%20whose%20noise%20is%20challenging%20to%20characterize.%20Existing%20denoising%20methods%20for%20event%20cameras%20are%20often%20designed%20in%20isolation%20and%20thus%20consider%20other%20tasks%2C%20such%20as%20motion%20estimation%2C%20separately%20%28i.e.%2C%20sequentially%20after%20denoising%29.%20However%2C%20motion%20is%20an%20intrinsic%20part%20of%20event%20data%2C%20since%20scene%20edges%20cannot%20be%20sensed%20without%20motion.%20We%20propose%2C%20to%20the%20best%20of%20our%20knowledge%2C%20the%20first%20method%20that%20simultaneously%20estimates%20motion%20in%20its%20various%20forms%20%28e.g.%2C%20ego-motion%2C%20optical%20flow%29%20and%20noise.%20The%20method%20is%20flexible%2C%20as%20it%20allows%20replacing%20the%20one-step%20motion%20estimation%20of%20the%20widely-used%20Contrast%20Maximization%20framework%20with%20any%20other%20motion%20estimator%2C%20such%20as%20deep%20neural%20networks.%20The%20experiments%20show%20that%20the%20proposed%20method%20achieves%20state-of-the-art%20results%20on%20the%20E-MLB%20denoising%20benchmark%20and%20competitive%20results%20on%20the%20DND21%20benchmark%2C%20while%20demonstrating%20effectiveness%20across%20motion%20estimation%20and%20intensity%20reconstruction%20tasks.%20Our%20approach%20advances%20event-data%20denoising%20theory%20and%20expands%20practical%20denoising%20use-cases%20via%20open-source%20code.%20Project%20page%3A%20https%3A%5C%2F%5C%2Fgithub.com%5C%2Ftub-rip%5C%2FESMD%22%2C%22proceedingsTitle%22%3A%222025%20IEEE%5C%2FCVF%20International%20Conference%20on%20Computer%20Vision%20%28ICCV%29%22%2C%22conferenceName%22%3A%222025%20IEEE%5C%2FCVF%20International%20Conference%20on%20Computer%20Vision%20%28ICCV%29%22%2C%22date%22%3A%222025-10%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FICCV51701.2025.00654%22%2C%22ISBN%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F11444130%22%2C%22ISSN%22%3A%222380-7504%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T12%3A04%3A01Z%22%7D%7D%2C%7B%22key%22%3A%22QQDS9SCB%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Yamaki%20et%20al.%22%2C%22parsedDate%22%3A%222025-06%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BYamaki%2C%20R.%2C%20Shiba%2C%20S.%2C%20Gallego%2C%20G.%2C%20%26amp%3B%20Aoki%2C%20Y.%20%282025%29.%20Iterative%20Event-Based%20Motion%20Segmentation%20by%20Variational%20Contrast%20Maximization.%20%26lt%3Bi%26gt%3B2025%20IEEE%5C%2FCVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20Workshops%20%28CVPRW%29%26lt%3B%5C%2Fi%26gt%3B%2C%204918%26%23x2013%3B4927.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FCVPRW67362.2025.00484%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FCVPRW67362.2025.00484%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Iterative%20Event-Based%20Motion%20Segmentation%20by%20Variational%20Contrast%20Maximization%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ryo%22%2C%22lastName%22%3A%22Yamaki%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shintaro%22%2C%22lastName%22%3A%22Shiba%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yoshimitsu%22%2C%22lastName%22%3A%22Aoki%22%7D%5D%2C%22abstractNote%22%3A%22Event%20cameras%20provide%20rich%20signals%20that%20are%20suitable%20for%20motion%20estimation%20since%20they%20respond%20to%20changes%20in%20the%20scene.%20As%20any%20visual%20changes%20in%20the%20scene%20produce%20event%20data%2C%20it%20is%20paramount%20to%20classify%20the%20data%20into%20different%20motions%20%28i.e.%2C%20motion%20segmentation%29%2C%20which%20is%20useful%20for%20various%20tasks%20such%20as%20object%20detection%20and%20visual%20servoing.%20We%20pro-pose%20an%20iterative%20motion%20segmentation%20method%2C%20by%20classifying%20events%20into%20background%20%28e.g.%2C%20dominant%20motion%20hypoth-esis%29%20and%20foreground%20%28independent%20motion%20residuals%29%2C%20thus%20extending%20the%20Contrast%20Maximization%20framework.%20Experi-mental%20results%20demonstrate%20that%20the%20proposed%20method%20suc-cessfully%20classifies%20event%20clusters%20both%20for%20public%20and%20self-recorded%20datasets%2C%20producing%20sharp%2C%20motion-compensated%20edge-like%20images.%20The%20proposed%20method%20achieves%20state-of-the-art%20accuracy%20on%20moving%20object%20detection%20benchmarks%20with%20an%20improvement%20of%20over%2030%25%2C%20and%20demonstrates%20its%20possibility%20of%20applying%20to%20more%20complex%20and%20noisy%20real-world%20scenes.%20We%20hope%20this%20work%20broadens%20the%20sensitiv-ity%20of%20Contrast%20Maximization%20with%20respect%20to%20both%20motion%20parameters%20and%20input%20events%2C%20thus%20contributing%20to%20theoret-ical%20advancements%20in%20event-based%20motion%20segmentation%20es-timation.%20https%3A%5C%2F%5C%2Fgithub.com%5C%2Faoki-media-lab%5C%2Fevent_based_segmentation.vcmax%22%2C%22proceedingsTitle%22%3A%222025%20IEEE%5C%2FCVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20Workshops%20%28CVPRW%29%22%2C%22conferenceName%22%3A%222025%20IEEE%5C%2FCVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20Workshops%20%28CVPRW%29%22%2C%22date%22%3A%222025-06%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FCVPRW67362.2025.00484%22%2C%22ISBN%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fabstract%5C%2Fdocument%5C%2F11147623%22%2C%22ISSN%22%3A%222160-7516%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A16Z%22%7D%7D%2C%7B%22key%22%3A%22QRHVCW7L%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Hamann%20et%20al.%22%2C%22parsedDate%22%3A%222025-06%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BHamann%2C%20F.%2C%20Gehrig%2C%20D.%2C%20Febryanto%2C%20F.%2C%20Daniilidis%2C%20K.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282025%29.%20ETAP%3A%20Event-based%20Tracking%20of%20Any%20Point.%20%26lt%3Bi%26gt%3B2025%20IEEE%5C%2FCVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20%28CVPR%29%26lt%3B%5C%2Fi%26gt%3B%2C%2027186%26%23x2013%3B27196.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FCVPR52734.2025.02532%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FCVPR52734.2025.02532%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22ETAP%3A%20Event-based%20Tracking%20of%20Any%20Point%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Friedhelm%22%2C%22lastName%22%3A%22Hamann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daniel%22%2C%22lastName%22%3A%22Gehrig%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Filbert%22%2C%22lastName%22%3A%22Febryanto%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kostas%22%2C%22lastName%22%3A%22Daniilidis%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22Tracking%20any%20point%20%28TAP%29%20recently%20shifted%20the%20motion%20estimation%20paradigm%20from%20focusing%20on%20individual%20salient%20points%20with%20local%20templates%20to%20tracking%20arbitrary%20points%20with%20global%20image%20contexts.%20However%2C%20while%20research%20has%20mostly%20focused%20on%20driving%20the%20accuracy%20of%20models%20in%20nominal%20settings%2C%20addressing%20scenarios%20with%20difficult%20lighting%20conditions%20and%20high-speed%20motions%20remains%20out%20of%20reach%20due%20to%20the%20limitations%20of%20the%20sensor.%20This%20work%20addresses%20this%20challenge%20with%20the%20first%20event%20camera-based%20TAP%20method.%20It%20leverages%20the%20high%20temporal%20resolution%20and%20high%20dynamic%20range%20of%20event%20cameras%20for%20robust%20high-speed%20tracking%2C%20and%20the%20global%20contexts%20in%20TAP%20methods%20to%20handle%20asynchronous%20and%20sparse%20event%20measurements.%20We%20further%20extend%20the%20TAP%20framework%20to%20handle%20event%20feature%20variations%20induced%20by%20motion%20%5Cu2014%20thereby%20addressing%20an%20open%20challenge%20in%20purely%20event-based%20tracking%20%5Cu2014%20with%20a%20novel%20feature%20alignment-loss%20which%20ensures%20the%20learning%20of%20motion-robust%20features.%20Our%20method%20is%20trained%20with%20data%20from%20a%20new%20data%20generation%20pipeline%20and%20systematically%20ablated%20across%20all%20design%20decisions.%20Our%20method%20shows%20strong%20cross-dataset%20generalization%20and%20performs%20136%25%20better%20on%20the%20average%20Jaccard%20metric%20than%20the%20baselines.%20Moreover%2C%20on%20an%20established%20feature%20tracking%20benchmark%2C%20it%20achieves%20a%2020%25%20improvement%20over%20the%20previous%20best%20event-only%20method%20and%20even%20surpasses%20the%20previous%20best%20events-and-frames%20method%20by%204.1%25.%20Our%20code%20is%20available%20at%20https%3A%5C%2F%5C%2Fgithub.com%5C%2Ftub-rip%5C%2FETAP.%22%2C%22proceedingsTitle%22%3A%222025%20IEEE%5C%2FCVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20%28CVPR%29%22%2C%22conferenceName%22%3A%222025%20IEEE%5C%2FCVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20%28CVPR%29%22%2C%22date%22%3A%222025-06%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FCVPR52734.2025.02532%22%2C%22ISBN%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F11094223%22%2C%22ISSN%22%3A%222575-7075%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T12%3A03%3A32Z%22%7D%7D%2C%7B%22key%22%3A%22W7B6NDYG%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Wang%20et%20al.%22%2C%22parsedDate%22%3A%222025-06%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BWang%2C%20Z.%2C%20Hamann%2C%20F.%2C%20Chaney%2C%20K.%2C%20Jiang%2C%20W.%2C%20Gallego%2C%20G.%2C%20%26amp%3B%20Daniilidis%2C%20K.%20%282025%29.%20Event-Based%20Continuous%20Color%20Video%20Decompression%20from%20Single%20Frames.%20%26lt%3Bi%26gt%3B2025%20IEEE%5C%2FCVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20Workshops%20%28CVPRW%29%26lt%3B%5C%2Fi%26gt%3B%2C%204968%26%23x2013%3B4978.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FCVPRW67362.2025.00490%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FCVPRW67362.2025.00490%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Event-Based%20Continuous%20Color%20Video%20Decompression%20from%20Single%20Frames%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ziyun%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Friedhelm%22%2C%22lastName%22%3A%22Hamann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kenneth%22%2C%22lastName%22%3A%22Chaney%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Wen%22%2C%22lastName%22%3A%22Jiang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kostas%22%2C%22lastName%22%3A%22Daniilidis%22%7D%5D%2C%22abstractNote%22%3A%22We%20present%20ContinuityCam%2C%20a%20novel%20approach%20to%20generate%20a%20continuous%20video%20from%20a%20single%20static%20RGB%20image%20and%20an%20event%20camera%20stream.%20Conventional%20cameras%20struggle%20with%20high-speed%20motion%20capture%20due%20to%20bandwidth%20and%20dynamic%20range%20limitations.%20Event%20cameras%20are%20ideal%20sensors%20to%20solve%20this%20problem%20because%20they%20encode%20compressed%20change%20information%20at%20high%20temporal%20resolution.%20In%20this%20work%2C%20we%20tackle%20the%20problem%20of%20event-based%20continuous%20color%20video%20decompression%2C%20pairing%20single%20static%20color%20frames%20and%20event%20data%20to%20reconstruct%20temporally%20continuous%20videos.%20Our%20approach%20combines%20continuous%20long-range%20motion%20modeling%20with%20a%20neural%20synthesis%20model%2C%20enabling%20frame%20prediction%20at%20arbitrary%20times%20within%20the%20events.%20Our%20method%20only%20requires%20an%20initial%20image%2C%20thus%20increasing%20the%20robustness%20to%20sudden%20motions%2C%20light%20changes%2C%20minimizing%20the%20prediction%20latency%2C%20and%20decreasing%20bandwidth%20usage.%20We%20also%20introduce%20a%20novel%20single-lens%20beamsplitter%20setup%20that%20acquires%20aligned%20images%20and%20events%2C%20and%20a%20novel%20and%20challenging%20Event%20Extreme%20Decompression%20Dataset%20%28E2D2%29%20that%20tests%20the%20method%20in%20various%20lighting%20and%20motion%20profiles.%20We%20thoroughly%20evaluate%20our%20method%20by%20benchmarking%20color%20frame%20reconstruction%2C%20outperforming%20the%20baseline%20methods%20by%203.61%20dB%20in%20PSNR%20and%20by%2033%25%20decrease%20in%20LPIPS%2C%20as%20well%20as%20showing%20superior%20results%20on%20two%20downstream%20tasks.%20Please%20see%20our%20project%20website%20for%20details%3A%20https%3A%5C%2F%5C%2Fwww.cis.upenn.edu%5C%2F%20ziyunw%5C%2Fcontinuity_cam%5C%2F.%22%2C%22proceedingsTitle%22%3A%222025%20IEEE%5C%2FCVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20Workshops%20%28CVPRW%29%22%2C%22conferenceName%22%3A%222025%20IEEE%5C%2FCVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20Workshops%20%28CVPRW%29%22%2C%22date%22%3A%222025-06%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FCVPRW67362.2025.00490%22%2C%22ISBN%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F11147662%22%2C%22ISSN%22%3A%222160-7516%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T12%3A01%3A40Z%22%7D%7D%2C%7B%22key%22%3A%22GKG63NAI%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Reinold%20et%20al.%22%2C%22parsedDate%22%3A%222025-02-28%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BReinold%2C%20T.%2C%20Ghosh%2C%20S.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282025%29.%20Combined%20Physics%20and%20Event%20Camera%20Simulator%20for%20Slip%20Detection.%20%26lt%3Bi%26gt%3B2025%20IEEE%5C%2FCVF%20Winter%20Conference%20on%20Applications%20of%20Computer%20Vision%20Workshops%20%28WACVW%29%26lt%3B%5C%2Fi%26gt%3B%2C%20872%26%23x2013%3B880.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FWACVW65960.2025.00104%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FWACVW65960.2025.00104%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Combined%20Physics%20and%20Event%20Camera%20Simulator%20for%20Slip%20Detection%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Thilo%22%2C%22lastName%22%3A%22Reinold%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Suman%22%2C%22lastName%22%3A%22Ghosh%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22proceedingsTitle%22%3A%222025%20IEEE%5C%2FCVF%20Winter%20Conference%20on%20Applications%20of%20Computer%20Vision%20Workshops%20%28WACVW%29%22%2C%22conferenceName%22%3A%222025%20IEEE%5C%2FCVF%20Winter%20Conference%20on%20Applications%20of%20Computer%20Vision%20Workshops%20%28WACVW%29%22%2C%22date%22%3A%222025-2-28%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FWACVW65960.2025.00104%22%2C%22ISBN%22%3A%22979-8-3315-3662-6%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F10972644%5C%2F%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A59%3A16Z%22%7D%7D%2C%7B%22key%22%3A%22SNCG6RHQ%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Hamann%20et%20al.%22%2C%22parsedDate%22%3A%222025%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BHamann%2C%20F.%2C%20Ghosh%2C%20S.%2C%20Ju%26%23xE1%3Brez%20Mart%26%23xED%3Bnez%2C%20I.%2C%20Hart%2C%20T.%2C%20Kacelnik%2C%20A.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282025%29.%20Fourier%26%23x2010%3BBased%20Action%20Recognition%20for%20Wildlife%20Behavior%20Quantification%20with%20Event%20Cameras.%20%26lt%3Bi%26gt%3BAdvanced%20Intelligent%20Systems%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B7%26lt%3B%5C%2Fi%26gt%3B%282%29%2C%202400353.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1002%5C%2Faisy.202400353%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1002%5C%2Faisy.202400353%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Fourier%5Cu2010Based%20Action%20Recognition%20for%20Wildlife%20Behavior%20Quantification%20with%20Event%20Cameras%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Friedhelm%22%2C%22lastName%22%3A%22Hamann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Suman%22%2C%22lastName%22%3A%22Ghosh%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ignacio%22%2C%22lastName%22%3A%22Ju%5Cu00e1rez%20Mart%5Cu00ednez%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tom%22%2C%22lastName%22%3A%22Hart%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alex%22%2C%22lastName%22%3A%22Kacelnik%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22Event%20cameras%20are%20novel%20bioinspired%20vision%20sensors%20that%20measure%20pixel%5Cu2010wise%20brightness%20changes%20asynchronously%20instead%20of%20images%20at%20a%20given%20frame%20rate.%20They%20offer%20promising%20advantages%2C%20namely%2C%20a%20high%20dynamic%20range%2C%20low%20latency%2C%20and%20minimal%20motion%20blur.%20Modern%20computer%20vision%20algorithms%20often%20rely%20on%20artificial%20neural%20network%20approaches%2C%20which%20require%20image%5Cu2010like%20representations%20of%20the%20data%20and%20cannot%20fully%20exploit%20the%20characteristics%20of%20event%20data.%20Herein%2C%20approaches%20to%20action%20recognition%20based%20on%20the%20Fourier%20transform%20are%20proposed.%20The%20approaches%20are%20intended%20to%20recognize%20oscillating%20motion%20patterns%20commonly%20present%20in%20nature.%20In%20particular%2C%20the%20approaches%20are%20applied%20to%20a%20recent%20dataset%20of%20breeding%20penguins%20annotated%20for%20%5Cu201cecstatic%20display%2C%5Cu201d%20a%20behavior%20where%20the%20observed%20penguins%20flap%20their%20wings%20at%20a%20certain%20frequency.%20It%20is%20found%20that%20the%20approaches%20are%20both%20simple%20and%20effective%2C%20producing%20slightly%20lower%20results%20than%20a%20deep%20neural%20network%20%28DNN%29%20while%20relying%20just%20on%20a%20tiny%20fraction%20of%20the%20parameters%20compared%20to%20the%20DNN%20%28five%20orders%20of%20magnitude%20fewer%20parameters%29.%20They%20work%20well%20despite%20the%20uncontrolled%2C%20diverse%20data%20present%20in%20the%20dataset.%20It%20is%20hoped%20that%20this%20work%20opens%20a%20new%20perspective%20on%20event%5Cu2010based%20processing%20and%20action%20recognition.%22%2C%22date%22%3A%2202%5C%2F2025%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1002%5C%2Faisy.202400353%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fadvanced.onlinelibrary.wiley.com%5C%2Fdoi%5C%2F10.1002%5C%2Faisy.202400353%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%222640-4567%2C%202640-4567%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A57%3A38Z%22%7D%7D%2C%7B%22key%22%3A%22WJTBHM4B%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Hamann%20et%20al.%22%2C%22parsedDate%22%3A%222025%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BHamann%2C%20F.%2C%20Wang%2C%20Z.%2C%20Asmanis%2C%20I.%2C%20Chaney%2C%20K.%2C%20Gallego%2C%20G.%2C%20%26amp%3B%20Daniilidis%2C%20K.%20%282025%29.%20Motion-Prior%20Contrast%20Maximization%20for%26%23xA0%3BDense%20Continuous-Time%20Motion%20Estimation.%20In%20A.%20Leonardis%2C%20E.%20Ricci%2C%20S.%20Roth%2C%20O.%20Russakovsky%2C%20T.%20Sattler%2C%20%26amp%3B%20G.%20Varol%20%28Eds.%29%2C%20%26lt%3Bi%26gt%3BComputer%20Vision%20%26%23x2013%3B%20ECCV%202024%26lt%3B%5C%2Fi%26gt%3B%20%28pp.%2018%26%23x2013%3B37%29.%20Springer%20Nature%20Switzerland.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-72646-0_2%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-72646-0_2%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Motion-Prior%20Contrast%20Maximization%20for%5Cu00a0Dense%20Continuous-Time%20Motion%20Estimation%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Friedhelm%22%2C%22lastName%22%3A%22Hamann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ziyun%22%2C%22lastName%22%3A%22Wang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ioannis%22%2C%22lastName%22%3A%22Asmanis%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kenneth%22%2C%22lastName%22%3A%22Chaney%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kostas%22%2C%22lastName%22%3A%22Daniilidis%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Ale%5Cu0161%22%2C%22lastName%22%3A%22Leonardis%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Elisa%22%2C%22lastName%22%3A%22Ricci%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Stefan%22%2C%22lastName%22%3A%22Roth%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Olga%22%2C%22lastName%22%3A%22Russakovsky%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Torsten%22%2C%22lastName%22%3A%22Sattler%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22G%5Cu00fcl%22%2C%22lastName%22%3A%22Varol%22%7D%5D%2C%22abstractNote%22%3A%22Current%20optical%20flow%20and%20point-tracking%20methods%20rely%20heavily%20on%20synthetic%20datasets.%20Event%20cameras%20are%20novel%20vision%20sensors%20with%20advantages%20in%20challenging%20visual%20conditions%2C%20but%20state-of-the-art%20frame-based%20methods%20cannot%20be%20easily%20adapted%20to%20event%20data%20due%20to%20the%20limitations%20of%20current%20event%20simulators.%20We%20introduce%20a%20novel%20self-supervised%20loss%20combining%20the%20Contrast%20Maximization%20framework%20with%20a%20non-linear%20motion%20prior%20in%20the%20form%20of%20pixel-level%20trajectories%20and%20propose%20an%20efficient%20solution%20to%20solve%20the%20high-dimensional%20assignment%20problem%20between%20non-linear%20trajectories%20and%20events.%20Their%20effectiveness%20is%20demonstrated%20in%20two%20scenarios%3A%20In%20dense%20continuous-time%20motion%20estimation%2C%20our%20method%20improves%20the%20zero-shot%20performance%20of%20a%20synthetically%20trained%20model%20on%20the%20real-world%20dataset%20EVIMO2%20by%2029%25.%20In%20optical%20flow%20estimation%2C%20our%20method%20elevates%20a%20simple%20UNet%20to%20achieve%20state-of-the-art%20performance%20among%20self-supervised%20methods%20on%20the%20DSEC%20optical%20flow%20benchmark.%20Our%20code%20is%20available%20at%20https%3A%5C%2F%5C%2Fgithub.com%5C%2Ftub-rip%5C%2FMotionPriorCMax.%22%2C%22proceedingsTitle%22%3A%22Computer%20Vision%20%5Cu2013%20ECCV%202024%22%2C%22conferenceName%22%3A%22%22%2C%22date%22%3A%222025%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1007%5C%2F978-3-031-72646-0_2%22%2C%22ISBN%22%3A%22978-3-031-72646-0%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A16Z%22%7D%7D%2C%7B%22key%22%3A%22HW7H7YAS%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Ren%20et%20al.%22%2C%22parsedDate%22%3A%222025%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BRen%2C%20Z.%2C%20Liao%2C%20B.%2C%20Kong%2C%20D.%2C%20Li%2C%20J.%2C%20Liu%2C%20P.%2C%20Kneip%2C%20L.%2C%20Gallego%2C%20G.%2C%20%26amp%3B%20Zhou%2C%20Y.%20%282025%29.%20Motion%20and%26%23xA0%3BStructure%20from%26%23xA0%3BEvent-Based%20Normal%20Flow.%20In%20A.%20Leonardis%2C%20E.%20Ricci%2C%20S.%20Roth%2C%20O.%20Russakovsky%2C%20T.%20Sattler%2C%20%26amp%3B%20G.%20Varol%20%28Eds.%29%2C%20%26lt%3Bi%26gt%3BComputer%20Vision%20%26%23x2013%3B%20ECCV%202024%26lt%3B%5C%2Fi%26gt%3B%20%28pp.%20108%26%23x2013%3B125%29.%20Springer%20Nature%20Switzerland.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-72992-8_7%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-72992-8_7%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Motion%20and%5Cu00a0Structure%20from%5Cu00a0Event-Based%20Normal%20Flow%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zhongyang%22%2C%22lastName%22%3A%22Ren%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Bangyan%22%2C%22lastName%22%3A%22Liao%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Delei%22%2C%22lastName%22%3A%22Kong%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jinghang%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Peidong%22%2C%22lastName%22%3A%22Liu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Laurent%22%2C%22lastName%22%3A%22Kneip%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yi%22%2C%22lastName%22%3A%22Zhou%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Ale%5Cu0161%22%2C%22lastName%22%3A%22Leonardis%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Elisa%22%2C%22lastName%22%3A%22Ricci%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Stefan%22%2C%22lastName%22%3A%22Roth%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Olga%22%2C%22lastName%22%3A%22Russakovsky%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Torsten%22%2C%22lastName%22%3A%22Sattler%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22G%5Cu00fcl%22%2C%22lastName%22%3A%22Varol%22%7D%5D%2C%22abstractNote%22%3A%22Recovering%20the%20camera%20motion%20and%20scene%20geometry%5Cu00a0from%20visual%20data%20is%20a%20fundamental%20problem%20in%20computer%20vision.%20Its%20success%20in%20conventional%20%28frame-based%29%20vision%20is%20attributed%20to%20the%20maturity%20of%20feature%20extraction%2C%20data%20association%20and%20multi-view%20geometry.%5Cu00a0The%20emergence%20of%20asynchronous%20%28event-based%29%20cameras%20calls%20for%5Cu00a0new%20approaches%20that%20use%20raw%20event%20data%20as%20input%20to%20solve%5Cu00a0this%20fundamental%20problem.%20State-of-the-art%20solutions%20typically%20infer%5Cu00a0data%20association%20implicitly%20by%20iteratively%20reversing%20the%20event%5Cu00a0data%20generation%20process.%20However%2C%20the%20nonlinear%20nature%20of%20these%20methods%20limits%20their%20applicability%20in%20real-time%20tasks%2C%20and%5Cu00a0the%20constant-motion%20assumption%20leads%20to%20unstable%20results%20under%5Cu00a0agile%20motion.%20To%20this%20end%2C%20we%20reformulate%20the%20problem%20in%20a%20way%20that%20aligns%20better%20with%20the%20differential%20working%20principle%20of%20event%20cameras.%5Cu00a0We%20show%20that%20event-based%20normal%20flow%20can%20be%20used%2C%20via%20the%20proposed%20geometric%20error%20term%2C%20as%20an%20alternative%20to%20the%20full%20%28optical%29%5Cu00a0flow%20in%20solving%20a%20family%20of%20geometric%20problems%20that%20involve%20instantaneous%20first-order%20kinematics%20and%20scene%20geometry.%20Furthermore%2C%20we%20develop%5Cu00a0a%20fast%20linear%20solver%20and%20a%20continuous-time%20nonlinear%20solver%20on%20top%5Cu00a0of%20the%20proposed%20geometric%20error%20term.%20Experiments%20on%20both%20synthetic%5Cu00a0and%20real%20data%20show%20the%20superiority%20of%20our%20linear%20solver%20in%20terms%5Cu00a0of%20accuracy%20and%20efficiency%2C%20and%20its%20practicality%20as%20an%20initializer%5Cu00a0for%20previous%20nonlinear%20solvers.%20Besides%2C%20our%20continuous-time%20non-linear%20solver%20exhibits%20exceptional%20capabilities%20in%20accommodating%20sudden%20variations%20in%20motion%20since%20it%20does%20not%20rely%20on%20the%20constant-motion%20assumption.%20Our%20project%20page%20can%20be%20found%5Cu00a0at%20https%3A%5C%2F%5C%2Fnail-hnu.github.io%5C%2FEvLinearSolver%5C%2F.%22%2C%22proceedingsTitle%22%3A%22Computer%20Vision%20%5Cu2013%20ECCV%202024%22%2C%22conferenceName%22%3A%22%22%2C%22date%22%3A%222025%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1007%5C%2F978-3-031-72992-8_7%22%2C%22ISBN%22%3A%22978-3-031-72992-8%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A16Z%22%7D%7D%2C%7B%22key%22%3A%22CZNXPLGP%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Hamann%20et%20al.%22%2C%22parsedDate%22%3A%222025%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BHamann%2C%20F.%2C%20Li%2C%20H.%2C%20Mieske%2C%20P.%2C%20Lewejohann%2C%20L.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282025%29.%20MouseSIS%3A%20A%20Frames-and-Events%20Dataset%20for%26%23xA0%3BSpace-Time%20Instance%20Segmentation%20of%26%23xA0%3BMice.%20In%20A.%20Del%20Bue%2C%20C.%20Canton%2C%20J.%20Pont-Tuset%2C%20%26amp%3B%20T.%20Tommasi%20%28Eds.%29%2C%20%26lt%3Bi%26gt%3BComputer%20Vision%20%26%23x2013%3B%20ECCV%202024%20Workshops%26lt%3B%5C%2Fi%26gt%3B%20%28pp.%20156%26%23x2013%3B173%29.%20Springer%20Nature%20Switzerland.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-92460-6_10%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-92460-6_10%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22MouseSIS%3A%20A%20Frames-and-Events%20Dataset%20for%5Cu00a0Space-Time%20Instance%20Segmentation%20of%5Cu00a0Mice%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Friedhelm%22%2C%22lastName%22%3A%22Hamann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Hanxiong%22%2C%22lastName%22%3A%22Li%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Paul%22%2C%22lastName%22%3A%22Mieske%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Lars%22%2C%22lastName%22%3A%22Lewejohann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Alessio%22%2C%22lastName%22%3A%22Del%20Bue%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Cristian%22%2C%22lastName%22%3A%22Canton%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Jordi%22%2C%22lastName%22%3A%22Pont-Tuset%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Tatiana%22%2C%22lastName%22%3A%22Tommasi%22%7D%5D%2C%22abstractNote%22%3A%22Enabled%20by%20large%20annotated%20datasets%2C%20tracking%20and%20segmentation%20of%20objects%20in%20videos%20has%20made%20remarkable%20progress%20in%20recent%20years.%20Despite%20these%20advancements%2C%20algorithms%20still%20struggle%20under%20degraded%20conditions%20and%20during%20fast%20movements.%20Event%20cameras%20are%20novel%20sensors%20with%20high%20temporal%20resolution%20and%20high%20dynamic%20range%20that%20offer%20promising%20advantages%20to%20address%20these%20challenges.%20However%2C%20annotated%20data%20for%20developing%20learning-based%20mask-level%20tracking%20algorithms%20with%20events%20is%20not%20available.%20To%20this%20end%2C%20we%20introduce%3A%20%28i%29%20a%20new%20task%20termed%20space-time%20instance%20segmentation%2C%20similar%20to%20video%20instance%20segmentation%2C%20whose%20goal%20is%20to%20segment%20instances%20throughout%20the%20entire%20duration%20of%20the%20sensor%20input%20%28here%2C%20the%20input%20are%20quasi-continuous%20events%20and%20optionally%20aligned%20frames%29%3B%20and%20%28ii%29%20MouseSIS%2C%20a%20dataset%20for%20the%20new%20task%2C%20containing%20aligned%20grayscale%20frames%20and%20events.%20It%20includes%20annotated%20ground-truth%20labels%20%28pixel-level%20instance%20segmentation%20masks%29%20of%20a%20group%20of%20up%20to%20seven%20freely%20moving%20and%20interacting%20mice.%20We%20also%20provide%20two%20reference%20methods%2C%20which%20show%20that%20leveraging%20event%20data%20can%20consistently%20improve%20tracking%20performance%2C%20especially%20when%20used%20in%20combination%20with%20conventional%20cameras.%20The%20results%20highlight%20the%20potential%20of%20event-aided%20tracking%20in%20difficult%20scenarios.%20We%20hope%20our%20dataset%20opens%20the%20field%20of%20event-based%20video%20instance%20segmentation%20and%20enables%20the%20development%20of%20robust%20tracking%20algorithms%20for%20challenging%20conditions.%20https%3A%5C%2F%5C%2Fgithub.com%5C%2Ftub-rip%5C%2FMouseSIS%22%2C%22proceedingsTitle%22%3A%22Computer%20Vision%20%5Cu2013%20ECCV%202024%20Workshops%22%2C%22conferenceName%22%3A%22%22%2C%22date%22%3A%222025%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1007%5C%2F978-3-031-92460-6_10%22%2C%22ISBN%22%3A%22978-3-031-92460-6%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A16Z%22%7D%7D%2C%7B%22key%22%3A%224K6RG2KQ%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Niu%20et%20al.%22%2C%22parsedDate%22%3A%222025%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BNiu%2C%20J.%2C%20Zhong%2C%20S.%2C%20Lu%2C%20X.%2C%20Shen%2C%20S.%2C%20Gallego%2C%20G.%2C%20%26amp%3B%20Zhou%2C%20Y.%20%282025%29.%20ESVO2%3A%20Direct%20Visual-Inertial%20Odometry%20With%20Stereo%20Event%20Cameras.%20%26lt%3Bi%26gt%3BIEEE%20Transactions%20on%20Robotics%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B41%26lt%3B%5C%2Fi%26gt%3B%2C%202164%26%23x2013%3B2183.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTRO.2025.3548523%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTRO.2025.3548523%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22ESVO2%3A%20Direct%20Visual-Inertial%20Odometry%20With%20Stereo%20Event%20Cameras%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Junkai%22%2C%22lastName%22%3A%22Niu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Sheng%22%2C%22lastName%22%3A%22Zhong%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Xiuyuan%22%2C%22lastName%22%3A%22Lu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shaojie%22%2C%22lastName%22%3A%22Shen%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yi%22%2C%22lastName%22%3A%22Zhou%22%7D%5D%2C%22abstractNote%22%3A%22Event-based%20visual%20odometry%20is%20a%20specific%20branch%20of%20visual%20simultaneous%20localization%20and%20mapping%20%28SLAM%29%20techniques%2C%20which%20aims%20at%20solving%20tracking%20and%20mapping%20subproblems%20%28typically%20in%20parallel%29%2C%20by%20exploiting%20the%20special%20working%20principles%20of%20neuromorphic%20%28i.e.%2C%20event-based%29%20cameras.%20Due%20to%20the%20motion-dependent%20nature%20of%20event%20data%2C%20explicit%20data%20association%20%28i.e.%2C%20feature%20matching%29%20under%20large-baseline%20viewpoint%20changes%20is%20difficult%20to%20establish%2C%20making%20direct%20methods%20a%20more%20rational%20choice.%20However%2C%20state-of-the-art%20direct%20methods%20are%20limited%20by%20the%20high%20computational%20complexity%20of%20the%20mapping%20subproblem%20and%20the%20degeneracy%20of%20camera%20pose%20tracking%20in%20certain%20degrees%20of%20freedom%20%28DoF%29%20in%20rotation.%20In%20this%20article%2C%20we%20tackle%20these%20issues%20by%20building%20an%20event-based%20stereo%20visual-inertial%20odometry%20system%2C%20which%20is%20built%20upon%20a%20direct%20pipeline%20known%20as%20event-based%20stereo%20visual%20odometry%20%28ESVO%29.%20Specifically%2C%20to%20speed%20up%20the%20mapping%20operation%2C%20we%20propose%20an%20efficient%20strategy%20for%20sampling%20contour%20points%20according%20to%20the%20local%20dynamics%20of%20events.%20The%20mapping%20performance%20is%20also%20improved%20in%20terms%20of%20structure%20completeness%20and%20local%20smoothness%20by%20merging%20the%20temporal%20stereo%20and%20static%20stereo%20results.%20To%20circumvent%20the%20degeneracy%20of%20camera%20pose%20tracking%20in%20recovering%20the%20pitch%20and%20yaw%20components%20of%20general%206-DoF%20motion%2C%20we%20introduce%20IMU%20measurements%20as%20motion%20priors%20via%20preintegration.%20To%20this%20end%2C%20a%20compact%20back-end%20is%20proposed%20for%20continuously%20updating%20the%20IMU%20bias%20and%20predicting%20the%20linear%20velocity%2C%20enabling%20an%20accurate%20motion%20prediction%20for%20camera%20pose%20tracking.%20The%20resulting%20system%20scales%20well%20with%20modern%20high-resolution%20event%20cameras%20and%20leads%20to%20better%20global%20positioning%20accuracy%20in%20large-scale%20outdoor%20environments.%20Extensive%20evaluations%20on%20five%20publicly%20available%20datasets%20featuring%20different%20resolutions%20and%20scenarios%20justify%20the%20superior%20performance%20of%20the%20proposed%20system%20against%20five%20state-of-the-art%20methods.%20Compared%20to%20ESVO%2C%20our%20new%20pipeline%20significantly%20reduces%20the%20camera%20pose%20tracking%20error%20by%2040%25%5Cu201380%25%20and%2020%25%5Cu201380%25%20in%20terms%20of%20absolute%20trajectory%20error%20and%20relative%20pose%20error%2C%20respectively%3B%20at%20the%20same%20time%2C%20the%20mapping%20efficiency%20is%20improved%20by%20a%20factor%20of%20five.%20We%20release%20our%20pipeline%20as%20an%20open-source%20software%20for%20future%20research%20in%20this%20field.%22%2C%22date%22%3A%222025%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FTRO.2025.3548523%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F10912788%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%221941-0468%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T12%3A02%3A58Z%22%7D%7D%2C%7B%22key%22%3A%22KTZMIFMD%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Ghosh%20et%20al.%22%2C%22parsedDate%22%3A%222025%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGhosh%2C%20S.%2C%20Cavinato%2C%20V.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282025%29.%20ES-PTAM%3A%20Event-Based%20Stereo%20Parallel%20Tracking%20and%26%23xA0%3BMapping.%20In%20A.%20Del%20Bue%2C%20C.%20Canton%2C%20J.%20Pont-Tuset%2C%20%26amp%3B%20T.%20Tommasi%20%28Eds.%29%2C%20%26lt%3Bi%26gt%3BComputer%20Vision%20%26%23x2013%3B%20ECCV%202024%20Workshops%26lt%3B%5C%2Fi%26gt%3B%20%28pp.%2070%26%23x2013%3B87%29.%20Springer%20Nature%20Switzerland.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-92460-6_5%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-92460-6_5%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22ES-PTAM%3A%20Event-Based%20Stereo%20Parallel%20Tracking%20and%5Cu00a0Mapping%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Suman%22%2C%22lastName%22%3A%22Ghosh%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Valentina%22%2C%22lastName%22%3A%22Cavinato%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Alessio%22%2C%22lastName%22%3A%22Del%20Bue%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Cristian%22%2C%22lastName%22%3A%22Canton%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Jordi%22%2C%22lastName%22%3A%22Pont-Tuset%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Tatiana%22%2C%22lastName%22%3A%22Tommasi%22%7D%5D%2C%22abstractNote%22%3A%22Visual%20Odometry%20%28VO%29%20and%20SLAM%20are%20fundamental%20components%20for%20spatial%20perception%20in%20mobile%20robots.%20Despite%20enormous%20progress%20in%20the%20field%2C%20current%20VO%5C%2FSLAM%20systems%20are%20limited%20by%20their%20sensors%5Cu2019%20capability.%20Event%20cameras%20are%20novel%20visual%20sensors%20that%20offer%20advantages%20to%20overcome%20the%20limitations%20of%20standard%20cameras%2C%20enabling%20robots%20to%20expand%20their%20operating%20range%20to%20challenging%20scenarios%2C%20such%20as%20high-speed%20motion%20and%20high%20dynamic%20range%20illumination.%20We%20propose%20a%20novel%20event-based%20stereo%20VO%20system%20by%20combining%20two%20ideas%3A%20a%20correspondence-free%20mapping%20module%20that%20estimates%20depth%20by%20maximizing%20ray%20density%20fusion%20and%20a%20tracking%20module%20that%20estimates%20camera%20poses%20by%20maximizing%20edge-map%20alignment.%20We%20evaluate%20the%20system%20comprehensively%20on%20five%20real-world%20datasets%2C%20spanning%20a%20variety%20of%20camera%20types%20%28manufacturers%20and%20spatial%20resolutions%29%20and%20scenarios%20%28driving%2C%20flying%20drone%2C%20hand-held%2C%20egocentric%2C%20etc.%29.%20The%20quantitative%20and%20qualitative%20results%20demonstrate%20that%20our%20method%20outperforms%20the%20state%20of%20the%20art%20in%20majority%20of%20the%20test%20sequences%20by%20a%20margin%2C%20e.g.%2C%20trajectory%20error%20reduction%20of%2045%25%20on%20RPG%20dataset%2C%2061%25%20on%20DSEC%20dataset%2C%20and%2021%25%20on%20TUM-VIE%20dataset.%20To%20benefit%20the%20community%20and%20foster%20research%20on%20event-based%20perception%20systems%2C%20we%20release%20the%20source%20code%20and%20results%3A%20https%3A%5C%2F%5C%2Fgithub.com%5C%2Ftub-rip%5C%2FES-PTAM.%22%2C%22proceedingsTitle%22%3A%22Computer%20Vision%20%5Cu2013%20ECCV%202024%20Workshops%22%2C%22conferenceName%22%3A%22%22%2C%22date%22%3A%222025%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1007%5C%2F978-3-031-92460-6_5%22%2C%22ISBN%22%3A%22978-3-031-92460-6%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T12%3A01%3A43Z%22%7D%7D%2C%7B%22key%22%3A%22NY736NDE%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Guo%20and%20Gallego%22%2C%22parsedDate%22%3A%222025%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGuo%2C%20S.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282025%29.%20Event-Based%20Mosaicing%20Bundle%20Adjustment.%20In%20A.%20Leonardis%2C%20E.%20Ricci%2C%20S.%20Roth%2C%20O.%20Russakovsky%2C%20T.%20Sattler%2C%20%26amp%3B%20G.%20Varol%20%28Eds.%29%2C%20%26lt%3Bi%26gt%3BComputer%20Vision%20%26%23x2013%3B%20ECCV%202024%26lt%3B%5C%2Fi%26gt%3B%20%28pp.%20479%26%23x2013%3B496%29.%20Springer%20Nature%20Switzerland.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-72624-8_27%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-72624-8_27%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Event-Based%20Mosaicing%20Bundle%20Adjustment%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shuang%22%2C%22lastName%22%3A%22Guo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Ale%5Cu0161%22%2C%22lastName%22%3A%22Leonardis%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Elisa%22%2C%22lastName%22%3A%22Ricci%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Stefan%22%2C%22lastName%22%3A%22Roth%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Olga%22%2C%22lastName%22%3A%22Russakovsky%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Torsten%22%2C%22lastName%22%3A%22Sattler%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22G%5Cu00fcl%22%2C%22lastName%22%3A%22Varol%22%7D%5D%2C%22abstractNote%22%3A%22We%20tackle%20the%20problem%20of%20mosaicing%20bundle%20adjustment%20%28i.e.%2C%20simultaneous%20refinement%20of%20camera%20orientations%20and%20scene%20map%29%20for%20a%20purely%20rotating%20event%20camera.%20We%20formulate%20the%20problem%20as%20a%20regularized%20non-linear%20least%20squares%20optimization.%20The%20objective%20function%20is%20defined%20using%20the%20linearized%20event%20generation%20model%20in%20the%20camera%20orientations%20and%20the%20panoramic%20gradient%20map%20of%20the%20scene.%20We%20show%20that%20this%20BA%20optimization%20has%20an%20exploitable%20block-diagonal%20sparsity%20structure%2C%20so%20that%20the%20problem%20can%20be%20solved%20efficiently.%20To%20the%20best%20of%20our%20knowledge%2C%20this%20is%20the%20first%20work%20to%20leverage%20such%20sparsity%20to%20speed%20up%20the%20optimization%20in%20the%20context%20of%20event-based%20cameras%2C%20without%20the%20need%20to%20convert%20events%20into%20image-like%20representations.%20We%20evaluate%20our%20method%2C%20called%20EMBA%2C%20on%20both%20synthetic%20and%20real-world%20datasets%20to%20show%20its%20effectiveness%20%2850%25%20photometric%20error%20decrease%29%2C%20yielding%20results%20of%20unprecedented%20quality.%20In%20addition%2C%20we%20demonstrate%20EMBA%20using%20high%20spatial%20resolution%20event%20cameras%2C%20yielding%20delicate%20panoramas%20in%20the%20wild%2C%20even%20without%20an%20initial%20map.%20The%20code%20is%20available%20at%20https%3A%5C%2F%5C%2Fgithub.com%5C%2Ftub-rip%5C%2Femba.%22%2C%22proceedingsTitle%22%3A%22Computer%20Vision%20%5Cu2013%20ECCV%202024%22%2C%22conferenceName%22%3A%22%22%2C%22date%22%3A%222025%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1007%5C%2F978-3-031-72624-8_27%22%2C%22ISBN%22%3A%22978-3-031-72624-8%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T12%3A01%3A37Z%22%7D%7D%2C%7B%22key%22%3A%222Z62Q3W6%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Ghosh%20and%20Gallego%22%2C%22parsedDate%22%3A%222025%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGhosh%2C%20S.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282025%29.%20Event-based%20Stereo%20Depth%20Estimation%3A%20A%20Survey.%20%26lt%3Bi%26gt%3BIEEE%20Transactions%20on%20Pattern%20Analysis%20and%20Machine%20Intelligence%26lt%3B%5C%2Fi%26gt%3B%2C%201%26%23x2013%3B20.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTPAMI.2025.3586559%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTPAMI.2025.3586559%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Event-based%20Stereo%20Depth%20Estimation%3A%20A%20Survey%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Suman%22%2C%22lastName%22%3A%22Ghosh%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222025%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FTPAMI.2025.3586559%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F11078760%5C%2F%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%220162-8828%2C%202160-9292%2C%201939-3539%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A57%3A41Z%22%7D%7D%2C%7B%22key%22%3A%2225UWWP3Q%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Guo%20and%20Gallego%22%2C%22parsedDate%22%3A%222025%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGuo%2C%20S.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282025%29.%20Event-based%20Photometric%20Bundle%20Adjustment.%20%26lt%3Bi%26gt%3BIEEE%20Transactions%20on%20Pattern%20Analysis%20and%20Machine%20Intelligence%26lt%3B%5C%2Fi%26gt%3B%2C%201%26%23x2013%3B18.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTPAMI.2025.3586497%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTPAMI.2025.3586497%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Event-based%20Photometric%20Bundle%20Adjustment%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shuang%22%2C%22lastName%22%3A%22Guo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222025%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FTPAMI.2025.3586497%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F11072301%5C%2F%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%220162-8828%2C%202160-9292%2C%201939-3539%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A57%3A44Z%22%7D%7D%2C%7B%22key%22%3A%22IABM7PYQ%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Hamann%20et%20al.%22%2C%22parsedDate%22%3A%222024-06-16%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BHamann%2C%20F.%2C%20Ghosh%2C%20S.%2C%20Mart%26%23xED%3Bnez%2C%20I.%20J.%2C%20Hart%2C%20T.%2C%20Kacelnik%2C%20A.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282024%29.%20Low-power%2C%20Continuous%20Remote%20Behavioral%20Localization%20with%20Event%20Cameras.%20%26lt%3Bi%26gt%3B2024%20IEEE%5C%2FCVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20%28CVPR%29%26lt%3B%5C%2Fi%26gt%3B%2C%2018612%26%23x2013%3B18621.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FCVPR52733.2024.01761%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FCVPR52733.2024.01761%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Low-power%2C%20Continuous%20Remote%20Behavioral%20Localization%20with%20Event%20Cameras%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Friedhelm%22%2C%22lastName%22%3A%22Hamann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Suman%22%2C%22lastName%22%3A%22Ghosh%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Ignacio%20Ju%5Cu00e1rez%22%2C%22lastName%22%3A%22Mart%5Cu00ednez%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tom%22%2C%22lastName%22%3A%22Hart%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Alex%22%2C%22lastName%22%3A%22Kacelnik%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22proceedingsTitle%22%3A%222024%20IEEE%5C%2FCVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20%28CVPR%29%22%2C%22conferenceName%22%3A%222024%20IEEE%5C%2FCVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20%28CVPR%29%22%2C%22date%22%3A%222024-6-16%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FCVPR52733.2024.01761%22%2C%22ISBN%22%3A%22979-8-3503-5300-6%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F10658483%5C%2F%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A55%3A27Z%22%7D%7D%2C%7B%22key%22%3A%227AZSL69M%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Shiba%20et%20al.%22%2C%22parsedDate%22%3A%222024%22%2C%22numChildren%22%3A2%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BShiba%2C%20S.%2C%20Klose%2C%20Y.%2C%20Aoki%2C%20Y.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282024%29.%20Secrets%20of%20Event-Based%20Optical%20Flow%2C%20Depth%20and%20Ego-Motion%20Estimation%20by%20Contrast%20Maximization.%20%26lt%3Bi%26gt%3BIEEE%20Transactions%20on%20Pattern%20Analysis%20and%20Machine%20Intelligence%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B46%26lt%3B%5C%2Fi%26gt%3B%2812%29%2C%207742%26%23x2013%3B7759.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTPAMI.2024.3396116%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTPAMI.2024.3396116%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Secrets%20of%20Event-Based%20Optical%20Flow%2C%20Depth%20and%20Ego-Motion%20Estimation%20by%20Contrast%20Maximization%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shintaro%22%2C%22lastName%22%3A%22Shiba%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yannick%22%2C%22lastName%22%3A%22Klose%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yoshimitsu%22%2C%22lastName%22%3A%22Aoki%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%2212%5C%2F2024%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FTPAMI.2024.3396116%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F10517639%5C%2F%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%220162-8828%2C%202160-9292%2C%201939-3539%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A19Z%22%7D%7D%2C%7B%22key%22%3A%225GULNVV3%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Rodr%5Cu00edguez-G%5Cu00f3mez%20et%20al.%22%2C%22parsedDate%22%3A%222024%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BRodr%26%23xED%3Bguez-G%26%23xF3%3Bmez%2C%20J.%20P.%2C%20Dios%2C%20J.%20R.%20M.%2C%20Ollero%2C%20A.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282024%29.%20On%20the%20Benefits%20of%20Visual%20Stabilization%20for%20Frame-%20and%20Event-Based%20Perception.%20%26lt%3Bi%26gt%3BIEEE%20Robotics%20and%20Automation%20Letters%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B9%26lt%3B%5C%2Fi%26gt%3B%2810%29%2C%208802%26%23x2013%3B8809.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FLRA.2024.3450290%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FLRA.2024.3450290%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22On%20the%20Benefits%20of%20Visual%20Stabilization%20for%20Frame-%20and%20Event-Based%20Perception%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22J.P.%22%2C%22lastName%22%3A%22Rodr%5Cu00edguez-G%5Cu00f3mez%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22J.R.%20Mart%5Cu00ednez-de%22%2C%22lastName%22%3A%22Dios%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22A.%22%2C%22lastName%22%3A%22Ollero%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22G.%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%2210%5C%2F2024%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FLRA.2024.3450290%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F10648753%5C%2F%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%222377-3766%2C%202377-3774%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A57%3A47Z%22%7D%7D%2C%7B%22key%22%3A%22LBP5N7JQ%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Wischow%20et%20al.%22%2C%22parsedDate%22%3A%222024%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BWischow%2C%20M.%2C%20Irmisch%2C%20P.%2C%20Boerner%2C%20A.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282024%29.%20Real%26%23x2010%3BTime%20Noise%20Source%20Estimation%20of%20a%20Camera%20System%20from%20an%20Image%20and%20Metadata.%20%26lt%3Bi%26gt%3BAdvanced%20Intelligent%20Systems%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B6%26lt%3B%5C%2Fi%26gt%3B%286%29%2C%202300479.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1002%5C%2Faisy.202300479%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1002%5C%2Faisy.202300479%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Real%5Cu2010Time%20Noise%20Source%20Estimation%20of%20a%20Camera%20System%20from%20an%20Image%20and%20Metadata%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Maik%22%2C%22lastName%22%3A%22Wischow%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Patrick%22%2C%22lastName%22%3A%22Irmisch%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anko%22%2C%22lastName%22%3A%22Boerner%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22Autonomous%20machines%20must%20self%5Cu2010maintain%20proper%20functionality%20to%20ensure%20the%20safety%20of%20humans%20and%20themselves.%20This%20pertains%20particularly%20to%20its%20cameras%20as%20predominant%20sensors%20to%20perceive%20the%20environment%20and%20support%20actions.%20A%20fundamental%20camera%20problem%20addressed%20in%20this%20study%20is%20noise.%20Solutions%20often%20focus%20on%20denoising%20images%20a%20posteriori%2C%20that%20is%2C%20fighting%20symptoms%20rather%20than%20root%20causes.%20However%2C%20tackling%20root%20causes%20requires%20identifying%20the%20noise%20sources%2C%20considering%20the%20limitations%20of%20mobile%20platforms.%20In%20this%20work%2C%20a%20real%5Cu2010time%2C%20memory%5Cu2010efficient%2C%20and%20reliable%20noise%20source%20estimator%20that%20combines%20data%5Cu2010based%20and%20physically%20based%20models%20is%20investigated.%20To%20this%20end%2C%20a%20deep%20neural%20network%20that%20examines%20an%20image%20with%20camera%20metadata%20for%20major%20camera%20noise%20sources%20is%20built%20and%20trained.%20In%20addition%2C%20it%20quantifies%20unexpected%20factors%20that%20impact%20image%20noise%20or%20metadata.%20This%20study%20investigates%20seven%20different%20estimators%20on%20six%20datasets%20that%20include%20synthetic%20noise%2C%20real%5Cu2010world%20noise%20from%20two%20camera%20systems%2C%20and%20real%5Cu2010field%20campaigns.%20For%20these%2C%20only%20the%20model%20with%20most%20metadata%20is%20capable%20to%20accurately%20and%20robustly%20quantify%20all%20individual%20noise%20contributions.%20This%20method%20outperforms%20total%20image%20noise%20estimators%20and%20can%20be%20plug%5Cu2010and%5Cu2010play%20deployed.%20It%20also%20serves%20as%20a%20basis%20to%20include%20more%20advanced%20noise%20sources%2C%20or%20as%20part%20of%20an%20automatic%20countermeasure%20feedback%20loop%20to%20approach%20fully%20reliable%20machines.%22%2C%22date%22%3A%2206%5C%2F2024%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1002%5C%2Faisy.202300479%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fonlinelibrary.wiley.com%5C%2Fdoi%5C%2F10.1002%5C%2Faisy.202300479%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%222640-4567%2C%202640-4567%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A20Z%22%7D%7D%2C%7B%22key%22%3A%229IFDXGX9%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Shiba%20et%20al.%22%2C%22parsedDate%22%3A%222024%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BShiba%2C%20S.%2C%20Hamann%2C%20F.%2C%20Aoki%2C%20Y.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282024%29.%20Event-Based%20Background-Oriented%20Schlieren.%20%26lt%3Bi%26gt%3BIEEE%20Transactions%20on%20Pattern%20Analysis%20and%20Machine%20Intelligence%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B46%26lt%3B%5C%2Fi%26gt%3B%284%29%2C%202011%26%23x2013%3B2026.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTPAMI.2023.3328188%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTPAMI.2023.3328188%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Event-Based%20Background-Oriented%20Schlieren%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shintaro%22%2C%22lastName%22%3A%22Shiba%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Friedhelm%22%2C%22lastName%22%3A%22Hamann%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yoshimitsu%22%2C%22lastName%22%3A%22Aoki%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%224%5C%2F2024%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FTPAMI.2023.3328188%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F10301562%5C%2F%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%220162-8828%2C%202160-9292%2C%201939-3539%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A54%3A54Z%22%7D%7D%2C%7B%22key%22%3A%224XNEYSFD%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Guo%20and%20Gallego%22%2C%22parsedDate%22%3A%222024%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGuo%2C%20S.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282024%29.%20CMax-SLAM%3A%20Event-Based%20Rotational-Motion%20Bundle%20Adjustment%20and%20SLAM%20System%20Using%20Contrast%20Maximization.%20%26lt%3Bi%26gt%3BIEEE%20Transactions%20on%20Robotics%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B40%26lt%3B%5C%2Fi%26gt%3B%2C%202442%26%23x2013%3B2461.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTRO.2024.3378443%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTRO.2024.3378443%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22CMax-SLAM%3A%20Event-Based%20Rotational-Motion%20Bundle%20Adjustment%20and%20SLAM%20System%20Using%20Contrast%20Maximization%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shuang%22%2C%22lastName%22%3A%22Guo%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222024%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FTRO.2024.3378443%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F10474186%5C%2F%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%221552-3098%2C%201941-0468%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A55%3A52Z%22%7D%7D%2C%7B%22key%22%3A%22SG585GIJ%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Shiba%20et%20al.%22%2C%22parsedDate%22%3A%222023%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BShiba%2C%20S.%2C%20Aoki%2C%20Y.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282023%29.%20A%20Fast%20Geometric%20Regularizer%20to%20Mitigate%20Event%20Collapse%20in%20the%20Contrast%20Maximization%20Framework.%20%26lt%3Bi%26gt%3BAdvanced%20Intelligent%20Systems%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B5%26lt%3B%5C%2Fi%26gt%3B%283%29%2C%202200251.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1002%5C%2Faisy.202200251%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1002%5C%2Faisy.202200251%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22A%20Fast%20Geometric%20Regularizer%20to%20Mitigate%20Event%20Collapse%20in%20the%20Contrast%20Maximization%20Framework%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shintaro%22%2C%22lastName%22%3A%22Shiba%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yoshimitsu%22%2C%22lastName%22%3A%22Aoki%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22Event%20cameras%20are%20emerging%20vision%20sensors%20and%20their%20advantages%20are%20suitable%20for%20various%20applications%20such%20as%20autonomous%20robots.%20Contrast%20maximization%20%28CMax%29%2C%20which%20provides%20state%5Cu2010of%5Cu2010the%5Cu2010art%20accuracy%20on%20motion%20estimation%20using%20events%2C%20may%20suffer%20from%20an%20overfitting%20problem%20called%20event%20collapse.%20Prior%20works%20are%20computationally%20expensive%20or%20cannot%20alleviate%20the%20overfitting%2C%20which%20undermines%20the%20benefits%20of%20the%20CMax%20framework.%20A%20novel%2C%20computationally%20efficient%20regularizer%20based%20on%20geometric%20principles%20to%20mitigate%20event%20collapse%20is%20proposed.%20The%20experiments%20show%20that%20the%20proposed%20regularizer%20achieves%20state%5Cu2010of%5Cu2010the%5Cu2010art%20accuracy%20results%2C%20while%20its%20reduced%20computational%20complexity%20makes%20it%20two%20to%20four%20times%20faster%20than%20previous%20approaches.%20To%20the%20best%20of%20our%20knowledge%2C%20this%20regularizer%20is%20the%20only%20effective%20solution%20for%20event%20collapse%20without%20trading%20off%20the%20runtime.%20It%20is%20hoped%20that%20this%20work%20opens%20the%20door%20for%20future%20applications%20that%20unlocks%20the%20advantages%20of%20event%20cameras.%20Project%20page%3A%20https%3A%5C%2F%5C%2Fgithub.com%5C%2Ftub%5Cu2010rip%5C%2Fevent_collapse%22%2C%22date%22%3A%2203%5C%2F2023%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1002%5C%2Faisy.202200251%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fonlinelibrary.wiley.com%5C%2Fdoi%5C%2F10.1002%5C%2Faisy.202200251%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%222640-4567%2C%202640-4567%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A50%3A28Z%22%7D%7D%2C%7B%22key%22%3A%22AFC5GJCM%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Shiba%20et%20al.%22%2C%22parsedDate%22%3A%222022-07-11%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BShiba%2C%20S.%2C%20Aoki%2C%20Y.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282022%29.%20Event%20Collapse%20in%20Contrast%20Maximization%20Frameworks.%20%26lt%3Bi%26gt%3BSensors%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B22%26lt%3B%5C%2Fi%26gt%3B%2814%29%2C%205190.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.3390%5C%2Fs22145190%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.3390%5C%2Fs22145190%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Event%20Collapse%20in%20Contrast%20Maximization%20Frameworks%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shintaro%22%2C%22lastName%22%3A%22Shiba%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yoshimitsu%22%2C%22lastName%22%3A%22Aoki%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22Contrast%20maximization%20%28CMax%29%20is%20a%20framework%20that%20provides%20state-of-the-art%20results%20on%20several%20event-based%20computer%20vision%20tasks%2C%20such%20as%20ego-motion%20or%20optical%20flow%20estimation.%20However%2C%20it%20may%20suffer%20from%20a%20problem%20called%20event%20collapse%2C%20which%20is%20an%20undesired%20solution%20where%20events%20are%20warped%20into%20too%20few%20pixels.%20As%20prior%20works%20have%20largely%20ignored%20the%20issue%20or%20proposed%20workarounds%2C%20it%20is%20imperative%20to%20analyze%20this%20phenomenon%20in%20detail.%20Our%20work%20demonstrates%20event%20collapse%20in%20its%20simplest%20form%20and%20proposes%20collapse%20metrics%20by%20using%20first%20principles%20of%20space%5Cu2013time%20deformation%20based%20on%20differential%20geometry%20and%20physics.%20We%20experimentally%20show%20on%20publicly%20available%20datasets%20that%20the%20proposed%20metrics%20mitigate%20event%20collapse%20and%20do%20not%20harm%20well-posed%20warps.%20To%20the%20best%20of%20our%20knowledge%2C%20regularizers%20based%20on%20the%20proposed%20metrics%20are%20the%20only%20effective%20solution%20against%20event%20collapse%20in%20the%20experimental%20settings%20considered%2C%20compared%20with%20other%20methods.%20We%20hope%20that%20this%20work%20inspires%20further%20research%20to%20tackle%20more%20complex%20warp%20models.%22%2C%22date%22%3A%222022-07-11%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.3390%5C%2Fs22145190%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fwww.mdpi.com%5C%2F1424-8220%5C%2F22%5C%2F14%5C%2F5190%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%221424-8220%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A59%3A32Z%22%7D%7D%2C%7B%22key%22%3A%22NFGRDPNM%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Gallego%20et%20al.%22%2C%22parsedDate%22%3A%222022-01-01%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGallego%2C%20G.%2C%20Delbruck%2C%20T.%2C%20Orchard%2C%20G.%2C%20Bartolozzi%2C%20C.%2C%20Taba%2C%20B.%2C%20Censi%2C%20A.%2C%20Leutenegger%2C%20S.%2C%20Davison%2C%20A.%20J.%2C%20Conradt%2C%20J.%2C%20Daniilidis%2C%20K.%2C%20%26amp%3B%20Scaramuzza%2C%20D.%20%282022%29.%20Event-Based%20Vision%3A%20A%20Survey.%20%26lt%3Bi%26gt%3BIEEE%20Transactions%20on%20Pattern%20Analysis%20and%20Machine%20Intelligence%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B44%26lt%3B%5C%2Fi%26gt%3B%281%29%2C%20154%26%23x2013%3B180.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTPAMI.2020.3008413%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTPAMI.2020.3008413%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Event-Based%20Vision%3A%20A%20Survey%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Tobi%22%2C%22lastName%22%3A%22Delbruck%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Garrick%22%2C%22lastName%22%3A%22Orchard%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Chiara%22%2C%22lastName%22%3A%22Bartolozzi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Brian%22%2C%22lastName%22%3A%22Taba%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Andrea%22%2C%22lastName%22%3A%22Censi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Stefan%22%2C%22lastName%22%3A%22Leutenegger%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Andrew%20J.%22%2C%22lastName%22%3A%22Davison%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Jorg%22%2C%22lastName%22%3A%22Conradt%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Kostas%22%2C%22lastName%22%3A%22Daniilidis%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Davide%22%2C%22lastName%22%3A%22Scaramuzza%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222022-1-1%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FTPAMI.2020.3008413%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F9138762%5C%2F%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%220162-8828%2C%202160-9292%2C%201939-3539%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A59%3A21Z%22%7D%7D%2C%7B%22key%22%3A%22YV8BRWS9%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Hidalgo-Carrio%20et%20al.%22%2C%22parsedDate%22%3A%222022%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BHidalgo-Carrio%2C%20J.%2C%20Gallego%2C%20G.%2C%20%26amp%3B%20Scaramuzza%2C%20D.%20%282022%29.%20Event-aided%20Direct%20Sparse%20Odometry.%20%26lt%3Bi%26gt%3B2022%20IEEE%5C%2FCVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20%28CVPR%29%26lt%3B%5C%2Fi%26gt%3B%2C%205771%26%23x2013%3B5780.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FCVPR52688.2022.00569%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FCVPR52688.2022.00569%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Event-aided%20Direct%20Sparse%20Odometry%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Javier%22%2C%22lastName%22%3A%22Hidalgo-Carrio%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Davide%22%2C%22lastName%22%3A%22Scaramuzza%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22proceedingsTitle%22%3A%222022%20IEEE%5C%2FCVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20%28CVPR%29%22%2C%22conferenceName%22%3A%222022%20IEEE%5C%2FCVF%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition%20%28CVPR%29%22%2C%22date%22%3A%226%5C%2F2022%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FCVPR52688.2022.00569%22%2C%22ISBN%22%3A%22978-1-6654-6946-3%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F9879881%5C%2F%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A59%3A29Z%22%7D%7D%2C%7B%22key%22%3A%22G6FWUVDR%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Ghosh%20and%20Gallego%22%2C%22parsedDate%22%3A%222022%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGhosh%2C%20S.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282022%29.%20%26lt%3Bi%26gt%3BEvent-based%20Stereo%20Depth%20Estimation%20from%20Ego-motion%20using%20Ray%20Density%20Fusion%26lt%3B%5C%2Fi%26gt%3B.%202nd%20International%20Ego4D%20Workshop%20at%20ECCV.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2210.08927%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2210.08927%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22presentation%22%2C%22title%22%3A%22Event-based%20Stereo%20Depth%20Estimation%20from%20Ego-motion%20using%20Ray%20Density%20Fusion%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Suman%22%2C%22lastName%22%3A%22Ghosh%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222022%22%2C%22sessionTitle%22%3A%22%22%2C%22DOI%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2210.08927%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A32Z%22%7D%7D%2C%7B%22key%22%3A%22D8CSCIQ9%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Shiba%20et%20al.%22%2C%22parsedDate%22%3A%222022%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BShiba%2C%20S.%2C%20Aoki%2C%20Y.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282022%29.%20Fast%20Event-Based%20Optical%20Flow%20Estimation%20by%20Triplet%20Matching.%20%26lt%3Bi%26gt%3BIEEE%20Signal%20Processing%20Letters%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B29%26lt%3B%5C%2Fi%26gt%3B%2C%202712%26%23x2013%3B2716.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FLSP.2023.3234800%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FLSP.2023.3234800%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Fast%20Event-Based%20Optical%20Flow%20Estimation%20by%20Triplet%20Matching%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shintaro%22%2C%22lastName%22%3A%22Shiba%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yoshimitsu%22%2C%22lastName%22%3A%22Aoki%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222022%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FLSP.2023.3234800%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F10008035%5C%2F%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%221070-9908%2C%201558-2361%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A24Z%22%7D%7D%2C%7B%22key%22%3A%22U8U3KZ65%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Ghosh%20and%20Gallego%22%2C%22parsedDate%22%3A%222022%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGhosh%2C%20S.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282022%29.%20Multi-Event-Camera%20Depth%20Estimation%20and%20Outlier%20Rejection%20by%20Refocused%20Events%20Fusion.%20%26lt%3Bi%26gt%3BAdvanced%20Intelligent%20Systems%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B4%26lt%3B%5C%2Fi%26gt%3B%2812%29%2C%202200221.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1002%5C%2Faisy.202200221%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1002%5C%2Faisy.202200221%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Multi-Event-Camera%20Depth%20Estimation%20and%20Outlier%20Rejection%20by%20Refocused%20Events%20Fusion%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Suman%22%2C%22lastName%22%3A%22Ghosh%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22Event%20cameras%20are%20bio-inspired%20sensors%20that%20offer%20advantages%20over%20traditional%20cameras.%20They%20operate%20asynchronously%2C%20sampling%20the%20scene%20at%20microsecond%20resolution%20and%20producing%20a%20stream%20of%20brightness%20changes.%20This%20unconventional%20output%20has%20sparked%20novel%20computer%20vision%20methods%20to%20unlock%20the%20camera%26%23039%3Bs%20potential.%20Here%2C%20the%20problem%20of%20event-based%20stereo%203D%20reconstruction%20for%20SLAM%20is%20considered.%20Most%20event-based%20stereo%20methods%20attempt%20to%20exploit%20the%20high%20temporal%20resolution%20of%20the%20camera%20and%20the%20simultaneity%20of%20events%20across%20cameras%20to%20establish%20matches%20and%20estimate%20depth.%20By%20contrast%2C%20this%20work%20investigates%20how%20to%20estimate%20depth%20without%20explicit%20data%20association%20by%20fusing%20disparity%20space%20images%20%28DSIs%29%20originated%20in%20efficient%20monocular%20methods.%20Fusion%20theory%20is%20developed%20and%20applied%20to%20design%20multi-camera%203D%20reconstruction%20algorithms%20that%20produce%20state-of-the-art%20results%2C%20as%20confirmed%20by%20comparisons%20with%20four%20baseline%20methods%20and%20tests%20on%20a%20variety%20of%20available%20datasets.%22%2C%22date%22%3A%222022%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1002%5C%2Faisy.202200221%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fonlinelibrary.wiley.com%5C%2Fdoi%5C%2Fabs%5C%2F10.1002%5C%2Faisy.202200221%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%222640-4567%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T12%3A06%3A05Z%22%7D%7D%2C%7B%22key%22%3A%22TL2EBCI2%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Shiba%20et%20al.%22%2C%22parsedDate%22%3A%222022%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BShiba%2C%20S.%2C%20Aoki%2C%20Y.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282022%29.%20Secrets%20of%20Event-Based%20Optical%20Flow.%20In%20S.%20Avidan%2C%20G.%20Brostow%2C%20M.%20Ciss%26%23xE9%3B%2C%20G.%20M.%20Farinella%2C%20%26amp%3B%20T.%20Hassner%20%28Eds.%29%2C%20%26lt%3Bi%26gt%3BComputer%20Vision%20%26%23x2013%3B%20ECCV%202022%26lt%3B%5C%2Fi%26gt%3B%20%28Vol.%2013678%2C%20pp.%20628%26%23x2013%3B645%29.%20Springer%20Nature%20Switzerland.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-19797-0_36%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1007%5C%2F978-3-031-19797-0_36%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22Secrets%20of%20Event-Based%20Optical%20Flow%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shintaro%22%2C%22lastName%22%3A%22Shiba%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yoshimitsu%22%2C%22lastName%22%3A%22Aoki%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Shai%22%2C%22lastName%22%3A%22Avidan%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Gabriel%22%2C%22lastName%22%3A%22Brostow%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Moustapha%22%2C%22lastName%22%3A%22Ciss%5Cu00e9%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Giovanni%20Maria%22%2C%22lastName%22%3A%22Farinella%22%7D%2C%7B%22creatorType%22%3A%22editor%22%2C%22firstName%22%3A%22Tal%22%2C%22lastName%22%3A%22Hassner%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22proceedingsTitle%22%3A%22Computer%20Vision%20%5Cu2013%20ECCV%202022%22%2C%22conferenceName%22%3A%22%22%2C%22date%22%3A%222022%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1007%5C%2F978-3-031-19797-0_36%22%2C%22ISBN%22%3A%22978-3-031-19796-3%20978-3-031-19797-0%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Flink.springer.com%5C%2F10.1007%5C%2F978-3-031-19797-0_36%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22en%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A49%3A39Z%22%7D%7D%2C%7B%22key%22%3A%22VIFCNETC%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Zhang%20et%20al.%22%2C%22parsedDate%22%3A%222022%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BZhang%2C%20Z.%2C%20Yezzi%2C%20A.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282022%29.%20Formulating%20Event-based%20Image%20Reconstruction%20as%20a%20Linear%20Inverse%20Problem%20with%20Deep%20Regularization%20using%20Optical%20Flow.%20%26lt%3Bi%26gt%3BIEEE%20Transactions%20on%20Pattern%20Analysis%20and%20Machine%20Intelligence%26lt%3B%5C%2Fi%26gt%3B%2C%201%26%23x2013%3B18.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTPAMI.2022.3230727%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTPAMI.2022.3230727%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Formulating%20Event-based%20Image%20Reconstruction%20as%20a%20Linear%20Inverse%20Problem%20with%20Deep%20Regularization%20using%20Optical%20Flow%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Zelin%22%2C%22lastName%22%3A%22Zhang%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Anthony%22%2C%22lastName%22%3A%22Yezzi%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%222022%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FTPAMI.2022.3230727%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F9994038%5C%2F%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%220162-8828%2C%202160-9292%2C%201939-3539%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A50%3A22Z%22%7D%7D%2C%7B%22key%22%3A%22ZQ2YPXZD%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Hamann%20and%20Gallego%22%2C%22parsedDate%22%3A%222022%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BHamann%2C%20F.%2C%20%26amp%3B%20Gallego%2C%20G.%20%282022%29.%20%26lt%3Bi%26gt%3BStereo%20Co-capture%20System%20for%20Recording%20and%20Tracking%20Fish%20with%20Frame-%20and%20Event%20Cameras%26lt%3B%5C%2Fi%26gt%3B%20%5BPoster%5D.%20Visual%20observation%20and%20analysis%20of%20Vertebrate%20And%20Insect%20Behavior%20%28VAIB%29%20Workshop%20at%20the%2026th%20International%20Conference%20on%20Pattern%20Recognition%20%28ICPR%29.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-ItemURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2207.07332%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2207.07332%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22presentation%22%2C%22title%22%3A%22Stereo%20Co-capture%20System%20for%20Recording%20and%20Tracking%20Fish%20with%20Frame-%20and%20Event%20Cameras%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Friedhelm%22%2C%22lastName%22%3A%22Hamann%22%7D%2C%7B%22creatorType%22%3A%22presenter%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%5D%2C%22abstractNote%22%3A%22This%20work%20introduces%20a%20co-capture%20system%20for%20multi-animal%20visual%20data%20acquisition%20using%20conventional%20cameras%20and%20event%20cameras.%20Event%20cameras%20offer%20multiple%20advantages%20over%20frame-based%20cameras%2C%20such%20as%20a%20high%20temporal%20resolution%20and%20temporal%20redundancy%20suppression%2C%20which%20enable%20us%20to%20efficiently%20capture%20the%20fast%20and%20erratic%20movements%20of%20fish.%20We%20furthermore%20present%20an%20event-based%20multi-animal%20tracking%20algorithm%2C%20which%20proves%20the%20feasibility%20of%20the%20approach%20and%20sets%20the%20baseline%20for%20further%20exploration%20of%20combining%20the%20advantages%20of%20event%20cameras%20and%20conventional%20cameras%20for%20multi-animal%20tracking.%22%2C%22date%22%3A%222022%22%2C%22sessionTitle%22%3A%22%22%2C%22DOI%22%3A%22%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Farxiv.org%5C%2Fabs%5C%2F2207.07332%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-09T12%3A56%3A03Z%22%7D%7D%2C%7B%22key%22%3A%22QFYITSBJ%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Gu%20et%20al.%22%2C%22parsedDate%22%3A%222021%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BGu%2C%20C.%2C%20Learned-Miller%2C%20E.%2C%20Sheldon%2C%20D.%2C%20Gallego%2C%20G.%2C%20%26amp%3B%20Bideau%2C%20P.%20%282021%29.%20The%20Spatio-Temporal%20Poisson%20Point%20Process%3A%20A%20Simple%20Model%20for%20the%20Alignment%20of%20Event%20Camera%20Data.%20%26lt%3Bi%26gt%3B2021%20IEEE%5C%2FCVF%20International%20Conference%20on%20Computer%20Vision%20%28ICCV%29%26lt%3B%5C%2Fi%26gt%3B%2C%2013475%26%23x2013%3B13484.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FICCV48922.2021.01324%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FICCV48922.2021.01324%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22conferencePaper%22%2C%22title%22%3A%22The%20Spatio-Temporal%20Poisson%20Point%20Process%3A%20A%20Simple%20Model%20for%20the%20Alignment%20of%20Event%20Camera%20Data%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Cheng%22%2C%22lastName%22%3A%22Gu%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Erik%22%2C%22lastName%22%3A%22Learned-Miller%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Daniel%22%2C%22lastName%22%3A%22Sheldon%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Pia%22%2C%22lastName%22%3A%22Bideau%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22proceedingsTitle%22%3A%222021%20IEEE%5C%2FCVF%20International%20Conference%20on%20Computer%20Vision%20%28ICCV%29%22%2C%22conferenceName%22%3A%222021%20IEEE%5C%2FCVF%20International%20Conference%20on%20Computer%20Vision%20%28ICCV%29%22%2C%22date%22%3A%2210%5C%2F2021%22%2C%22eventPlace%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FICCV48922.2021.01324%22%2C%22ISBN%22%3A%22978-1-6654-2812-5%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F9710557%5C%2F%22%2C%22ISSN%22%3A%22%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-29T10%3A40%3A24Z%22%7D%7D%2C%7B%22key%22%3A%22AH8YFERB%22%2C%22library%22%3A%7B%22id%22%3A6984777%7D%2C%22meta%22%3A%7B%22creatorSummary%22%3A%22Zhou%20et%20al.%22%2C%22parsedDate%22%3A%222021%22%2C%22numChildren%22%3A1%7D%2C%22bib%22%3A%22%26lt%3Bdiv%20class%3D%26quot%3Bcsl-bib-body%26quot%3B%20style%3D%26quot%3Bline-height%3A%202%3B%20padding-left%3A%201em%3B%20text-indent%3A-1em%3B%26quot%3B%26gt%3B%5Cn%20%20%26lt%3Bdiv%20class%3D%26quot%3Bcsl-entry%26quot%3B%26gt%3BZhou%2C%20Y.%2C%20Gallego%2C%20G.%2C%20%26amp%3B%20Shen%2C%20S.%20%282021%29.%20Event-Based%20Stereo%20Visual%20Odometry.%20%26lt%3Bi%26gt%3BIEEE%20Transactions%20on%20Robotics%26lt%3B%5C%2Fi%26gt%3B%2C%20%26lt%3Bi%26gt%3B37%26lt%3B%5C%2Fi%26gt%3B%285%29%2C%201433%26%23x2013%3B1450.%20%26lt%3Ba%20class%3D%26%23039%3Bzp-DOIURL%26%23039%3B%20href%3D%26%23039%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTRO.2021.3062252%26%23039%3B%26gt%3Bhttps%3A%5C%2F%5C%2Fdoi.org%5C%2F10.1109%5C%2FTRO.2021.3062252%26lt%3B%5C%2Fa%26gt%3B%26lt%3B%5C%2Fdiv%26gt%3B%5Cn%26lt%3B%5C%2Fdiv%26gt%3B%22%2C%22data%22%3A%7B%22itemType%22%3A%22journalArticle%22%2C%22title%22%3A%22Event-Based%20Stereo%20Visual%20Odometry%22%2C%22creators%22%3A%5B%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Yi%22%2C%22lastName%22%3A%22Zhou%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Guillermo%22%2C%22lastName%22%3A%22Gallego%22%7D%2C%7B%22creatorType%22%3A%22author%22%2C%22firstName%22%3A%22Shaojie%22%2C%22lastName%22%3A%22Shen%22%7D%5D%2C%22abstractNote%22%3A%22%22%2C%22date%22%3A%2210%5C%2F2021%22%2C%22section%22%3A%22%22%2C%22partNumber%22%3A%22%22%2C%22partTitle%22%3A%22%22%2C%22DOI%22%3A%2210.1109%5C%2FTRO.2021.3062252%22%2C%22citationKey%22%3A%22%22%2C%22url%22%3A%22https%3A%5C%2F%5C%2Fieeexplore.ieee.org%5C%2Fdocument%5C%2F9386209%5C%2F%22%2C%22PMID%22%3A%22%22%2C%22PMCID%22%3A%22%22%2C%22ISSN%22%3A%221552-3098%2C%201941-0468%22%2C%22language%22%3A%22%22%2C%22collections%22%3A%5B%5D%2C%22dateModified%22%3A%222026-06-22T11%3A59%3A25Z%22%7D%7D%5D%7D
Guo, S., Febryanto, F., Sun, L., & Gallego, G. (2026). Interp3R: Continuous-time 3D Geometry Estimation with Frames and Events (arXiv:2603.14528). arXiv. https://doi.org/10.48550/arXiv.2603.14528
Bartolomei, L., Tosi, F., Poggi, M., Mattoccia, S., & Gallego, G. (2026). EventHub: Data Factory for Generalizable Event-Based Stereo Networks without Active Sensors. IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR). https://bartn8.github.io/eventhub/
Kohyama, K., Aoki, Y., Gallego, G., & Shiba, S. (2026). Geometric-Photometric Event-based 3D Gaussian Ray Tracing. IEEE/CVF Computer Vision and Pattern Recognition Conference (CVPR). https://e3ai.github.io/gpert/
Gallego, G., Hidalgo-Carrió, J., & Scaramuzza, D. (2026). Event-based SLAM. In L. Carlone, A. Kim, T. Barfoot, D. Cremers, & F. Dellaert (Eds.), SLAM Handbook. From Localization and Mapping to Spatial Intelligence. Cambridge University Press. https://github.com/SLAM-Handbook-contributors/slam-handbook-public-release
Hitzges, D. de O., Ghosh, S., & Gallego, G. (2025, December). DERD-Net: Learning Depth from Event-based Ray Densities. 39th Annual Conference on Neural Information Processing Systems (NeurIPS). https://arxiv.org/abs/2504.15863
Guo, S., Hamann, F., & Gallego, G. (2025). Unsupervised Joint Learning of Optical Flow and Intensity with Event Cameras. 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 7980–7989. https://doi.org/10.1109/ICCV51701.2025.00748
Hamann, F., Mededovic, E., Gülhan, F., Wu, Y., Stegmaier, J., He, J., Wang, Y., Zhang, K., Li, L., Jiao, L., Ma, M., Huang, H., Yan, Y., Ren, H., Lin, X., Huang, Y., Cheng, B., Lee, S. H., Ham, G. S., … Gallego, G. (2025). SIS-Challenge: Event-Based Spatio-Temporal Instance Segmentation Challenge at the CVPR 2025 Event-Based Vision Workshop. 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 4734–4742. https://doi.org/10.1109/ICCVW69036.2025.00491
Shiba, S., Aoki, Y., & Gallego, G. (2025). Simultaneous Motion and Noise Estimation with Event Cameras. 2025 IEEE/CVF International Conference on Computer Vision (ICCV), 6959–6969. https://doi.org/10.1109/ICCV51701.2025.00654
Yamaki, R., Shiba, S., Gallego, G., & Aoki, Y. (2025). Iterative Event-Based Motion Segmentation by Variational Contrast Maximization. 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 4918–4927. https://doi.org/10.1109/CVPRW67362.2025.00484
Hamann, F., Gehrig, D., Febryanto, F., Daniilidis, K., & Gallego, G. (2025). ETAP: Event-based Tracking of Any Point. 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 27186–27196. https://doi.org/10.1109/CVPR52734.2025.02532
Wang, Z., Hamann, F., Chaney, K., Jiang, W., Gallego, G., & Daniilidis, K. (2025). Event-Based Continuous Color Video Decompression from Single Frames. 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 4968–4978. https://doi.org/10.1109/CVPRW67362.2025.00490
Reinold, T., Ghosh, S., & Gallego, G. (2025). Combined Physics and Event Camera Simulator for Slip Detection. 2025 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), 872–880. https://doi.org/10.1109/WACVW65960.2025.00104
Hamann, F., Ghosh, S., Juárez Martínez, I., Hart, T., Kacelnik, A., & Gallego, G. (2025). Fourier‐Based Action Recognition for Wildlife Behavior Quantification with Event Cameras. Advanced Intelligent Systems, 7(2), 2400353. https://doi.org/10.1002/aisy.202400353
Hamann, F., Wang, Z., Asmanis, I., Chaney, K., Gallego, G., & Daniilidis, K. (2025). Motion-Prior Contrast Maximization for Dense Continuous-Time Motion Estimation. In A. Leonardis, E. Ricci, S. Roth, O. Russakovsky, T. Sattler, & G. Varol (Eds.), Computer Vision – ECCV 2024 (pp. 18–37). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-72646-0_2
Ren, Z., Liao, B., Kong, D., Li, J., Liu, P., Kneip, L., Gallego, G., & Zhou, Y. (2025). Motion and Structure from Event-Based Normal Flow. In A. Leonardis, E. Ricci, S. Roth, O. Russakovsky, T. Sattler, & G. Varol (Eds.), Computer Vision – ECCV 2024 (pp. 108–125). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-72992-8_7
Hamann, F., Li, H., Mieske, P., Lewejohann, L., & Gallego, G. (2025). MouseSIS: A Frames-and-Events Dataset for Space-Time Instance Segmentation of Mice. In A. Del Bue, C. Canton, J. Pont-Tuset, & T. Tommasi (Eds.), Computer Vision – ECCV 2024 Workshops (pp. 156–173). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-92460-6_10
Niu, J., Zhong, S., Lu, X., Shen, S., Gallego, G., & Zhou, Y. (2025). ESVO2: Direct Visual-Inertial Odometry With Stereo Event Cameras. IEEE Transactions on Robotics, 41, 2164–2183. https://doi.org/10.1109/TRO.2025.3548523
Ghosh, S., Cavinato, V., & Gallego, G. (2025). ES-PTAM: Event-Based Stereo Parallel Tracking and Mapping. In A. Del Bue, C. Canton, J. Pont-Tuset, & T. Tommasi (Eds.), Computer Vision – ECCV 2024 Workshops (pp. 70–87). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-92460-6_5
Guo, S., & Gallego, G. (2025). Event-Based Mosaicing Bundle Adjustment. In A. Leonardis, E. Ricci, S. Roth, O. Russakovsky, T. Sattler, & G. Varol (Eds.), Computer Vision – ECCV 2024 (pp. 479–496). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-72624-8_27
Ghosh, S., & Gallego, G. (2025). Event-based Stereo Depth Estimation: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1–20. https://doi.org/10.1109/TPAMI.2025.3586559
Guo, S., & Gallego, G. (2025). Event-based Photometric Bundle Adjustment. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1–18. https://doi.org/10.1109/TPAMI.2025.3586497
Hamann, F., Ghosh, S., Martínez, I. J., Hart, T., Kacelnik, A., & Gallego, G. (2024). Low-power, Continuous Remote Behavioral Localization with Event Cameras. 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 18612–18621. https://doi.org/10.1109/CVPR52733.2024.01761
Shiba, S., Klose, Y., Aoki, Y., & Gallego, G. (2024). Secrets of Event-Based Optical Flow, Depth and Ego-Motion Estimation by Contrast Maximization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 7742–7759. https://doi.org/10.1109/TPAMI.2024.3396116
Rodríguez-Gómez, J. P., Dios, J. R. M., Ollero, A., & Gallego, G. (2024). On the Benefits of Visual Stabilization for Frame- and Event-Based Perception. IEEE Robotics and Automation Letters, 9(10), 8802–8809. https://doi.org/10.1109/LRA.2024.3450290
Wischow, M., Irmisch, P., Boerner, A., & Gallego, G. (2024). Real‐Time Noise Source Estimation of a Camera System from an Image and Metadata. Advanced Intelligent Systems, 6(6), 2300479. https://doi.org/10.1002/aisy.202300479
Shiba, S., Hamann, F., Aoki, Y., & Gallego, G. (2024). Event-Based Background-Oriented Schlieren. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(4), 2011–2026. https://doi.org/10.1109/TPAMI.2023.3328188
Guo, S., & Gallego, G. (2024). CMax-SLAM: Event-Based Rotational-Motion Bundle Adjustment and SLAM System Using Contrast Maximization. IEEE Transactions on Robotics, 40, 2442–2461. https://doi.org/10.1109/TRO.2024.3378443
Shiba, S., Aoki, Y., & Gallego, G. (2023). A Fast Geometric Regularizer to Mitigate Event Collapse in the Contrast Maximization Framework. Advanced Intelligent Systems, 5(3), 2200251. https://doi.org/10.1002/aisy.202200251
Shiba, S., Aoki, Y., & Gallego, G. (2022). Event Collapse in Contrast Maximization Frameworks. Sensors, 22(14), 5190. https://doi.org/10.3390/s22145190
Gallego, G., Delbruck, T., Orchard, G., Bartolozzi, C., Taba, B., Censi, A., Leutenegger, S., Davison, A. J., Conradt, J., Daniilidis, K., & Scaramuzza, D. (2022). Event-Based Vision: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(1), 154–180. https://doi.org/10.1109/TPAMI.2020.3008413
Hidalgo-Carrio, J., Gallego, G., & Scaramuzza, D. (2022). Event-aided Direct Sparse Odometry. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 5771–5780. https://doi.org/10.1109/CVPR52688.2022.00569
Ghosh, S., & Gallego, G. (2022). Event-based Stereo Depth Estimation from Ego-motion using Ray Density Fusion. 2nd International Ego4D Workshop at ECCV. https://arxiv.org/abs/2210.08927
Shiba, S., Aoki, Y., & Gallego, G. (2022). Fast Event-Based Optical Flow Estimation by Triplet Matching. IEEE Signal Processing Letters, 29, 2712–2716. https://doi.org/10.1109/LSP.2023.3234800
Ghosh, S., & Gallego, G. (2022). Multi-Event-Camera Depth Estimation and Outlier Rejection by Refocused Events Fusion. Advanced Intelligent Systems, 4(12), 2200221. https://doi.org/10.1002/aisy.202200221
Shiba, S., Aoki, Y., & Gallego, G. (2022). Secrets of Event-Based Optical Flow. In S. Avidan, G. Brostow, M. Cissé, G. M. Farinella, & T. Hassner (Eds.), Computer Vision – ECCV 2022 (Vol. 13678, pp. 628–645). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-19797-0_36
Zhang, Z., Yezzi, A., & Gallego, G. (2022). Formulating Event-based Image Reconstruction as a Linear Inverse Problem with Deep Regularization using Optical Flow. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1–18. https://doi.org/10.1109/TPAMI.2022.3230727
Hamann, F., & Gallego, G. (2022). Stereo Co-capture System for Recording and Tracking Fish with Frame- and Event Cameras [Poster]. Visual observation and analysis of Vertebrate And Insect Behavior (VAIB) Workshop at the 26th International Conference on Pattern Recognition (ICPR). https://arxiv.org/abs/2207.07332
Gu, C., Learned-Miller, E., Sheldon, D., Gallego, G., & Bideau, P. (2021). The Spatio-Temporal Poisson Point Process: A Simple Model for the Alignment of Event Camera Data. 2021 IEEE/CVF International Conference on Computer Vision (ICCV), 13475–13484. https://doi.org/10.1109/ICCV48922.2021.01324
Zhou, Y., Gallego, G., & Shen, S. (2021). Event-Based Stereo Visual Odometry. IEEE Transactions on Robotics, 37(5), 1433–1450. https://doi.org/10.1109/TRO.2021.3062252
Outstanding Associate Editor (IEEE Robotics Automation Letters, 2021)
PI Lecture -
Guillermo Gallego (Science of Intelligence), ” Beyond the Blink – New Applications and Methods for Event Cameras”
PI Lecture -
Guillermo Gallego (Science of Intelligence), “Event-based Vision at the TU Berlin Robotic Interactive Perception Lab”
For the Public -
Science of Intelligence Fair 2023
All electronics – June 2023 - Neue Art von Kamera bringt Robotern das menschliche Sehen bei
Tu Berlin – June 2023 - Eventkameras: eine völlig neue Art zu fotografieren
Tagesspiegel Beilage – November 2020 - Roboter mit Sinn für Orientierung
Tagesspiegel – November 2020 - Künstliche Intelligenz: Mit Sinn für Orientierung
