Compositional Human Pose Regression

Xiao Sun, Jiaxiang Shang, Shuang Liang, Yichen Wei; The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2602-2611

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.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Sun_2017_ICCV,
author = {Sun, Xiao and Shang, Jiaxiang and Liang, Shuang and Wei, Yichen},
title = {Compositional Human Pose Regression},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}