EventEgo3D: 3D Human Motion Capture from Egocentric Event Streams

TL;DR

EventEgo3D introduces a novel method for 3D human motion capture using egocentric event cameras, overcoming limitations of traditional RGB-based systems under challenging conditions like low light and fast motion.

Contribution

The paper presents the first approach for 3D human motion capture from egocentric monocular event streams, including a new dataset and a tailored learning framework.

Findings

Robust 3D pose estimation under high-speed motions and changing illumination.

Achieves real-time updates at 140Hz with high accuracy.

Outperforms existing methods in challenging scenarios.

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 approach to it called EventEgo3D (EE3D). Event streams have high temporal resolution and provide reliable cues for 3D human motion capture under high-speed 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 head-mounted device with an event camera and record a real dataset with event observations and the ground-truth 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 real-time 3D pose update rates of 140Hz.