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.
@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