English

Consistent 3D Hand Reconstruction in Video via self-supervised Learning

Computer Vision and Pattern Recognition 2023-03-21 v2 Artificial Intelligence

Abstract

We present a method for reconstructing accurate and consistent 3D hands from a monocular video. We observe that detected 2D hand keypoints and the image texture provide important cues about the geometry and texture of the 3D hand, which can reduce or even eliminate the requirement on 3D hand annotation. Thus we propose S2HAND{\rm {S}^{2}HAND}, a self-supervised 3D hand reconstruction model, that can jointly estimate pose, shape, texture, and the camera viewpoint from a single RGB input through the supervision of easily accessible 2D detected keypoints. We leverage the continuous hand motion information contained in the unlabeled video data and propose S2HAND(V){\rm {S}^{2}HAND(V)}, which uses a set of weights shared S2HAND{\rm {S}^{2}HAND} to process each frame and exploits additional motion, texture, and shape consistency constrains to promote more accurate hand poses and more consistent shapes and textures. Experiments on benchmark datasets demonstrate that our self-supervised approach produces comparable hand reconstruction performance compared with the recent full-supervised methods in single-frame as input setup, and notably improves the reconstruction accuracy and consistency when using video training data.

Keywords

Cite

@article{arxiv.2201.09548,
  title  = {Consistent 3D Hand Reconstruction in Video via self-supervised Learning},
  author = {Zhigang Tu and Zhisheng Huang and Yujin Chen and Di Kang and Linchao Bao and Bisheng Yang and Junsong Yuan},
  journal= {arXiv preprint arXiv:2201.09548},
  year   = {2023}
}

Comments

arXiv admin note: substantial text overlap with arXiv:2103.11703

R2 v1 2026-06-24T08:59:50.225Z