EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams

arXiv:2404.08640v1 Announce Type: new
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 head-mounted 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 …

abstract applications arxiv cameras cs.cv devices event head human lighting low motion capture sensors type visual