Paper Abstract:
Monocular egocentric 3D human motion capture is a challenging and actively researched problem. Existing methods use synchronously operating visual sensors (e.g. RGB cameras) and often fail under low lighting and fast motions, which can be restricting in many applications involving headmounted devices. In response to the existing limitations, this paper 1) introduces a new problem, i.e. 3D human motion capture from an egocentric monocular event camera with a fisheye lens, and 2) proposes the first approach to it called EventEgo3D (EE3D). Event streams have high temporal resolution and provide reliable cues for 3D human motion capture under highspeed human motions and rapidly changing illumination. The proposed EE3D framework is specifically tailored for learning with event streams in the LNES representation, enabling high 3D reconstruction accuracy. We also design a prototype of a mobile headmounted device with an event camera and record a real dataset with event observations and the groundtruth 3D human poses (in addition to the synthetic dataset). Our EE3D demonstrates robustness and superior 3D accuracy compared to existing solutions across various challenging experiments while supporting realtime 3D pose update rates of 140Hz.

Reference Publication: Christen Millerdurai, Hiroyasu Akada, Jian Wang, Diogo Luvizon, Christian Theobalt, Vladislav Golyanik .

EventEgo3D 3D Human Motion Capture from Egocentric Event Streams., CVPR, 2024.

Project Page: https://4dqv.mpiinf.mpg.de/EventEgo3D/