AI RESEARCH
Patient4D: Temporally Consistent Patient Body Mesh Recovery from Monocular Operating Room Video
arXiv CS.CV
•
ArXi:2603.17178v1 Announce Type: new Recovering a dense 3D body mesh from monocular video remains challenging under occlusion from draping and continuously moving camera viewpoints. This configuration arises in surgical augmented reality (AR), where an anesthetized patient lies under surgical draping while a surgeon's head-mounted camera continuously changes viewpoint. Existing human mesh recovery (HMR) methods are typically trained on upright, moving subjects captured from relatively stable cameras, leading to performance degradation under such conditions.