Probablistic Restoration with Adaptive Noise Sampling for 3D Human Pose Estimation

arXiv:2405.02114v1 Announce Type: new
Abstract: The accuracy and robustness of 3D human pose estimation (HPE) are limited by 2D pose detection errors and 2D to 3D ill-posed challenges, which have drawn great attention to Multi-Hypothesis HPE research. Most existing MH-HPE methods are based on generative models, which are computationally expensive and difficult to train. In this study, we propose a Probabilistic Restoration 3D Human Pose Estimation framework (PRPose) that can be integrated with any lightweight single-hypothesis model. Specifically, PRPose employs …

arxiv cs.cv human noise restoration sampling type