Cascaded Hand Pose Regression

Xiao Sun, Yichen Wei, Shuang Liang, Xiaoou Tang, Jian Sun

CVPR 2015

doi:10.1109/CVPR.2015.7298683 /cvpr/2015/sun2015cvpr-cascaded/

Abstract

We extends the previous 2D cascaded object pose regression work [9] in two aspects so that it works better for 3D articulated objects. Our first contribution is 3D pose-indexed features that generalize the previous 2D parameterized features and achieve better invariance to 3D transformations. Our second contribution is a principled hierarchical regression that is adapted to the articulated object structure. It is therefore more accurate and faster. Comprehensive experiments verify the state-of-the-art accuracy and efficiency of the proposed approach on the challenging 3D hand pose estimation problem, on a public dataset and our new dataset.

PDF CVPR Semantic Scholar

Cite

Text

Sun et al. "Cascaded Hand Pose Regression." Conference on Computer Vision and Pattern Recognition, 2015. doi:10.1109/CVPR.2015.7298683

Markdown

[Sun et al. "Cascaded Hand Pose Regression." Conference on Computer Vision and Pattern Recognition, 2015.](https://mlanthology.org/cvpr/2015/sun2015cvpr-cascaded/) doi:10.1109/CVPR.2015.7298683

BibTeX

@inproceedings{sun2015cvpr-cascaded,
  title     = {{Cascaded Hand Pose Regression}},
  author    = {Sun, Xiao and Wei, Yichen and Liang, Shuang and Tang, Xiaoou and Sun, Jian},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2015},
  doi       = {10.1109/CVPR.2015.7298683},
  url       = {https://mlanthology.org/cvpr/2015/sun2015cvpr-cascaded/}
}