HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloud

TL;DR

HandDiff introduces a diffusion-based approach for 3D hand pose estimation that effectively models keypoint permutation and localization, outperforming existing methods on multiple benchmarks.

Contribution

The paper presents a novel diffusion model for hand pose estimation that incorporates joint-wise and local detail conditions to improve accuracy.

Findings

Outperforms existing methods on four benchmark datasets.

Effectively models keypoint permutation and localization.

Provides publicly available code and pre-trained models.

Abstract

Extracting keypoint locations from input hand frames, known as 3D hand pose estimation, is a critical task in various human-computer interaction applications. Essentially, the 3D hand pose estimation can be regarded as a 3D point subset generative problem conditioned on input frames. Thanks to the recent significant progress on diffusion-based generative models, hand pose estimation can also benefit from the diffusion model to estimate keypoint locations with high quality. However, directly deploying the existing diffusion models to solve hand pose estimation is non-trivial, since they cannot achieve the complex permutation mapping and precise localization. Based on this motivation, this paper proposes HandDiff, a diffusion-based hand pose estimation model that iteratively denoises accurate hand pose conditioned on hand-shaped image-point clouds. In order to recover keypoint permutation and accurate location, we further introduce joint-wise condition and local detail condition. Experimental results demonstrate that the proposed HandDiff significantly outperforms the existing approaches on four challenging hand pose benchmark datasets. Codes and pre-trained models are publicly available at https://github.com/cwc1260/HandDiff.