Compositional Human Pose Regression

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 adop...

Full description

Saved in:
Bibliographic Details
Published inProceedings / IEEE International Conference on Computer Vision pp. 2621 - 2630
Main Authors Xiao Sun, Jiaxiang Shang, Shuang Liang, Yichen Wei
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2017
Subjects
Bones
Heating systems
Joints
Pose estimation
Solid modeling
Three-dimensional displays
Two dimensional displays
Online AccessGet full text

Cover

More Information
Summary: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 [20] and is competitive with state-of-the-art results on MPII [3].
ISSN:2380-7504
DOI:10.1109/ICCV.2017.284