Integral Human Pose Regression

State-of-the-art human pose estimation methods are based on heat map representation. In spite of the good performance, the representation has a few issues in nature, such as not differentiable and quantization error. This work shows that a simple integral operation relates and unifies the heat map representation and joint regression, thus avoiding the above issues. It is differentiable, efficient, and compatible with any heat map based methods. Its effectiveness is convincingly validated via comprehensive ablation experiments under various settings, specifically on 3D pose estimation, for the first time.

PDF Abstract ECCV 2018 PDF ECCV 2018 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Human Pose Estimation Human3.6M Integral Regression Average MPJPE (mm) 49.6 # 159
PA-MPJPE 40.6 # 59
Pose Estimation MPII Human Pose Integral Regression PCKh-0.5 91.0 # 23

Methods


No methods listed for this paper. Add relevant methods here