AI RESEARCH
Discriminative-Generative Synergy for Occlusion Robust 3D Human Mesh Recovery
arXiv CS.CV
•
ArXi:2604.21712v1 Announce Type: new 3D human mesh recovery from monocular RGB images aims to estimate anatomically plausible 3D human models for downstream applications, but remains challenging under partial or severe occlusions. Regression-based methods are efficient yet often produce implausible or inaccurate results in unconstrained scenarios, while diffusion-based methods provide strong generative priors for occluded regions but may weaken fidelity to rare poses due to over-reliance on generation.