HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos

TL;DR

HaWoR introduces a novel approach for reconstructing 3D hand motion in world coordinates from egocentric videos, utilizing a decoupled framework with an adaptive SLAM and motion infiller network, achieving state-of-the-art results.

Contribution

The paper presents a new method for world-space hand motion reconstruction from egocentric videos, including a robust SLAM framework and a motion infiller network, addressing limitations of existing single-image methods.

Findings

Achieves state-of-the-art performance on hand motion reconstruction.

Demonstrates robust camera trajectory estimation in egocentric videos.

Effectively completes missing hand motion frames with the motion infiller network.

Abstract

Despite the advent in 3D hand pose estimation, current methods predominantly focus on single-image 3D hand reconstruction in the camera frame, overlooking the world-space motion of the hands. Such limitation prohibits their direct use in egocentric video settings, where hands and camera are continuously in motion. In this work, we propose HaWoR, a high-fidelity method for hand motion reconstruction in world coordinates from egocentric videos. We propose to decouple the task by reconstructing the hand motion in the camera space and estimating the camera trajectory in the world coordinate system. To achieve precise camera trajectory estimation, we propose an adaptive egocentric SLAM framework that addresses the shortcomings of traditional SLAM methods, providing robust performance under challenging camera dynamics. To ensure robust hand motion trajectories, even when the hands move out of view frustum, we devise a novel motion infiller network that effectively completes the missing frames of the sequence. Through extensive quantitative and qualitative evaluations, we demonstrate that HaWoR achieves state-of-the-art performance on both hand motion reconstruction and world-frame camera trajectory estimation under different egocentric benchmark datasets. Code and models are available on https://hawor-project.github.io/ .