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 …

may reduce adaptation capacity of GCN to tackle complex spatio-temporal pose variations

… propose a novel Dynamical Graph Network (DG-Net), which can dynamically identify human-joint affinity, and estimate 3D pose by adaptively learning spatial/temporal joint relations from videos.

… discover spatial/temporal human-joint affinity for each video exemplar, depending on spatial distance/temporal movement similarity between human joints

… can effectively understand which joints are spatially closer and/or have consistent motion, for reducing depth ambiguity and/or motion uncertainty when lifting 2D pose to 3D pose.

… DG-Net outperforms a number of recent SOTA approaches with fewer input frames and model size.

Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website

LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b