HandDiff: 3D Hand Pose Estimation with Diffusion on Image-Point Cloud
This work addresses a critical task in human-computer interaction by enhancing 3D hand pose estimation, though it appears incremental as it builds on diffusion models with specific adaptations for hand data.
The paper tackled 3D hand pose estimation by proposing HandDiff, a diffusion-based model that iteratively denoises hand poses conditioned on image-point clouds, achieving significant performance improvements over existing approaches on four benchmark datasets.
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.