English

Compositional Human Pose Regression

Computer Vision and Pattern Recognition 2017-08-03 v3

Abstract

Regression based methods are not performing as well as detection based methods for human pose estimation. A central problem is that the structural information in the pose is not well exploited in the previous regression methods. In this work, we propose a structure-aware regression approach. It adopts a reparameterized pose representation using bones instead of joints. It exploits the joint connection structure to define a compositional loss function that encodes the long range interactions in the pose. It is simple, effective, and general for both 2D and 3D pose estimation in a unified setting. Comprehensive evaluation validates the effectiveness of our approach. It significantly advances the state-of-the-art on Human3.6M and is competitive with state-of-the-art results on MPII.

Keywords

Cite

@article{arxiv.1704.00159,
  title  = {Compositional Human Pose Regression},
  author = {Xiao Sun and Jiaxiang Shang and Shuang Liang and Yichen Wei},
  journal= {arXiv preprint arXiv:1704.00159},
  year   = {2017}
}

Comments

Accepted by International Conference on Computer Vision (ICCV) 2017

R2 v1 2026-06-22T19:04:29.648Z