AI RESEARCH
AugLift: Depth-Aware Input Reparameterization Improves Domain Generalization in 2D-to-3D Pose Lifting
arXiv CS.LG
•
ArXi:2508.07112v4 Announce Type: replace-cross Lifting-based 3D human pose estimation infers 3D joints from 2D keypoints but generalizes poorly because $(x,y)$ coordinates alone are an ill-posed, sparse representation that discards geometric information modern foundation models can recover.