Flow Matching for Probabilistic Monocular 3D Human Pose Estimation 事件

Flow Matching for Probabilistic Monocular 3D Human Pose Estimation arXiv:2601.16763v2 Announce Type: replace Abstract: Recovering 3D human poses from a monocular camera view is a highly ill-posed problem due to the depth ambiguity. Earlier studies on 3D human pose lifting from 2D often contain incorrect-yet-overconfident 3D estimations. To mitigate the problem, emerging probabilistic approaches treat the 3D estimations as a distribution, taking into account the uncertainty measurement of the po