PoseRN: A 2D pose refinement network for bias-free multi-view 3D human pose estimation

TL;DR

PoseRN is a novel 2D pose refinement network designed to eliminate human bias in 2D joint annotations, significantly improving the accuracy of multi-view 3D human pose estimation.

Contribution

The paper introduces a new network that effectively removes human bias from 2D pose estimates, enhancing multi-view 3D pose accuracy beyond existing methods.

Findings

Successfully removes human bias from 2D pose estimates

Achieves higher accuracy in multi-view 3D human pose estimation

Outperforms existing error reduction approaches

Abstract

We propose a new 2D pose refinement network that learns to predict the human bias in the estimated 2D pose. There are biases in 2D pose estimations that are due to differences between annotations of 2D joint locations based on annotators' perception and those defined by motion capture (MoCap) systems. These biases are crafted into publicly available 2D pose datasets and cannot be removed with existing error reduction approaches. Our proposed pose refinement network allows us to efficiently remove the human bias in the estimated 2D poses and achieve highly accurate multi-view 3D human pose estimation.