PoseRN: A 2D pose refinement network for bias-free multi-view 3D human pose estimation
This addresses a specific issue in computer vision for human pose estimation, but it is incremental as it builds on existing multi-view methods by refining 2D inputs.
The paper tackled the problem of biases in 2D pose estimations from annotator perception versus motion capture systems, which degrade multi-view 3D human pose estimation, and proposed a 2D pose refinement network to remove these biases, achieving highly accurate results.
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.