Personalized 3D Human Pose and Shape Refinement

arXiv:2403.11634v1 Announce Type: new
Abstract: Recently, regression-based methods have dominated the field of 3D human pose and shape estimation. Despite their promising results, a common issue is the misalignment between predictions and image observations, often caused by minor joint rotation errors that accumulate along the kinematic chain. To address this issue, we propose to construct dense correspondences between initial human model estimates and the corresponding images that can be used to refine the initial predictions. To this end, we utilize …

abstract arxiv cs.cv errors human image issue personalized predictions regression results rotation type