Better 3D pose estimates in video by dynamically learning joint relationships

Better 3D pose estimates in video by dynamically learning joint relationships

Learning Dynamical Human-Joint Affinity for 3D Pose Estimation in Videos
arXiv paper abstract https://arxiv.org/abs/2109.07353v1
arXiv PDF paper https://arxiv.org/pdf/2109.07353v1.pdf

Graph Convolution Network (GCN) … for 3D human pose estimation in videos. … built on the fixed human-joint affinity …