EgoEV-HandPose: Egocentric 3D Hand Pose Estimation and Gesture Recognition with Stereo Event Cameras

TL;DR

EgoEV-HandPose introduces a novel stereo event-camera framework and dataset for egocentric 3D hand pose estimation and gesture recognition, outperforming prior methods especially in challenging lighting and occlusion conditions.

Contribution

The paper presents EgoEV-HandPose, a new end-to-end stereo event-camera approach and the first large-scale dataset for egocentric hand perception, advancing state-of-the-art performance.

Findings

Achieves MPJPE of 30.54mm in hand pose estimation.

Attains 86.87% Top-1 gesture recognition accuracy.

Outperforms RGB-based and prior event-camera methods in low-light and occlusion scenarios.

Abstract

Egocentric 3D hand pose estimation and gesture recognition are essential for immersive augmented/virtual reality, human-computer interaction, and robotics. However, conventional frame-based cameras suffer from motion blur and limited dynamic range, while existing event-based methods are hindered by ego-motion interference, monocular depth ambiguity, and the lack of large-scale real-world stereo datasets. To overcome these limitations, we propose EgoEV-HandPose, an end-to-end framework for joint 3D bimanual pose estimation and gesture recognition from stereo event streams. Central to our approach is KeypointBEV, a flexible stereo fusion module that lifts features into a canonical bird's-eye-view space and employs an iterative reprojection-guided refinement loop to progressively resolve depth uncertainty and enforce kinematic consistency. In addition, we introduce EgoEVHands, the first large-scale real-world stereo event-camera dataset for egocentric hand perception, containing 5,419 annotated sequences with dense 3D/2D keypoints across 38 gesture classes under varying illumination. Extensive experiments demonstrate that EgoEV-HandPose achieves state-of-the-art performance with an MPJPE of 30.54mm and 86.87% Top-1 gesture recognition accuracy, significantly outperforming RGB-based stereo and prior event-camera methods, particularly in low-light and bimanual occlusion scenarios, thereby setting a new benchmark for event-based egocentric perception. The established dataset and source code will be publicly released at https://github.com/ZJUWang01/EgoEV-HandPose.