EvHandPose: Event-based 3D Hand Pose Estimation with Sparse Supervision

TL;DR

EvHandPose introduces a novel weakly-supervised framework with new hand flow representations for accurate 3D hand pose estimation from event camera data, effectively handling fast motion and high dynamic range scenarios.

Contribution

The paper proposes a new event-based hand pose estimation method with hand flow representations and a large-scale real-world dataset, addressing motion ambiguity and sparse annotation challenges.

Findings

Outperforms previous event-based methods across various scenes

Achieves high accuracy and stability in fast motion and high dynamic range conditions

Generalizes well to outdoor scenes and different event camera types

Abstract

Event camera shows great potential in 3D hand pose estimation, especially addressing the challenges of fast motion and high dynamic range in a low-power way. However, due to the asynchronous differential imaging mechanism, it is challenging to design event representation to encode hand motion information especially when the hands are not moving (causing motion ambiguity), and it is infeasible to fully annotate the temporally dense event stream. In this paper, we propose EvHandPose with novel hand flow representations in Event-to-Pose module for accurate hand pose estimation and alleviating the motion ambiguity issue. To solve the problem under sparse annotation, we design contrast maximization and hand-edge constraints in Pose-to-IWE (Image with Warped Events) module and formulate EvHandPose in a weakly-supervision framework. We further build EvRealHands, the first large-scale real-world event-based hand pose dataset on several challenging scenes to bridge the real-synthetic domain gap. Experiments on EvRealHands demonstrate that EvHandPose outperforms previous event-based methods under all evaluation scenes, achieves accurate and stable hand pose estimation with high temporal resolution in fast motion and strong light scenes compared with RGB-based methods, generalizes well to outdoor scenes and another type of event camera, and shows the potential for the hand gesture recognition task.