Vladislav Golyanik (MPI for Informatics), ” Egocentric 4D Vision with Conventional and Event Cameras”

4D computer vision using egocentric visual sensors on head-mounted devices (such as Aria glasses) is gaining momentum. While substantial progress has been made in recent years, various open challenges remain in the field, including robust 3D human and hand pose estimation from egocentric cameras, optimal egocentric camera placement, real-time processing, and fulfilling ergonomic and power consumption constraints of mobile devices. This talk will focus on several projects on egocentric 4D vision conducted by and with contributions from the 4D and Quantum Vision (4DQV) research group (MPI for Informatics). We will investigate how modern computer graphics rendering tools can be leveraged for synthetic training data generation, and discuss, among other points, the increasing role of event cameras in egocentric vision. The talk will also provide an overview of other ongoing research directions at 4DQV.

Bio:
Vladislav Golyanik is a senior researcher leading the “4D and Quantum Vision” research group at the Visual Computing and Artificial Intelligence (VCAI) Department of MPI for Informatics. He is also a lecturer at Saarland University. Vladislav’s primary research interests include 3D reconstruction and neural rendering of deformable scenes, 4D generative models and quantum-enhanced computer vision (QeCV). He received a doctoral degree in Computer Science from the University of Kaiserslautern in 2019.