Train Your Data Processor: Distribution-Aware and Error-Compensation Coordinate Decoding for Human Pose Estimation

by   Feiyu Yang, et al.

Recently, the leading performance of human pose estimation is dominated by heatmap based methods. While being a fundamental component of heatmap processing, heatmap decoding (i.e. transforming heatmaps to coordinates) receives only limited investigations, to our best knowledge. This work fills the gap by studying the heatmap decoding processing with a particular focus on the errors introduced throughout the prediction process. We found that the errors of heatmap based methods are surprisingly significant, which nevertheless was universally ignored before. In view of the discovered importance, we further reveal the intrinsic limitations of the previous widely used heatmap decoding methods and thereout propose a Distribution-Aware and Error-Compensation Coordinate Decoding (DAEC). Serving as a model-agnostic plug-in, DAEC learns its decoding strategy from training data and remarkably improves the performance of a variety of state-of-the-art human pose estimation models. Specifically, equipped with DAEC, the SimpleBaseline-ResNet152-256x192 and HRNet-W48-256x192 are significantly improved by 2.6 72.6 ResNet-152-256x256 frameworks enjoy even more dramatic promotions of 8.4 7.8 demonstrates that DAEC exceeds its competitors by considerable margins, backing up the rationality and generality of our novel heatmap decoding idea. The project is available at


Distribution-Aware Coordinate Representation for Human Pose Estimation

While being the de facto standard coordinate representation in human pos...

The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation

Recently, the leading performance of human pose estimation is dominated ...

GloPro: Globally-Consistent Uncertainty-Aware 3D Human Pose Estimation Tracking in the Wild

An accurate and uncertainty-aware 3D human body pose estimation is key t...

Human Pose Regression with Residual Log-likelihood Estimation

Heatmap-based methods dominate in the field of human pose estimation by ...

HTNet: Human Topology Aware Network for 3D Human Pose Estimation

3D human pose estimation errors would propagate along the human body top...

Human Pose as Compositional Tokens

Human pose is typically represented by a coordinate vector of body joint...

Please sign up or login with your details

Forgot password? Click here to reset