Patch-based 3D Human Pose Refinement
This work addresses the need for more precise 3D human pose estimation in computer vision applications, but it is incremental as it builds on existing state-of-the-art methods.
The paper tackles the problem of improving 3D human pose estimation by introducing a post-processing step that refines poses using local body part patches, which enhances accuracy by focusing on fine details and sharing part appearances across poses.
State-of-the-art 3D human pose estimation approaches typically estimate pose from the entire RGB image in a single forward run. In this paper, we develop a post-processing step to refine 3D human pose estimation from body part patches. Using local patches as input has two advantages. First, the fine details around body parts are zoomed in to high resolution for preciser 3D pose prediction. Second, it enables the part appearance to be shared between poses to benefit rare poses. In order to acquire informative representation of patches, we explore different input modalities and validate the superiority of fusing predicted segmentation with RGB. We show that our method consistently boosts the accuracy of state-of-the-art 3D human pose methods.