AI RESEARCH
H-Flow: Self-supervised Human Scene Flow via Physics-inspired Joint Multi-modal Learning
arXiv CS.CV
•
ArXi:2605.22629v1 Announce Type: new Parametric human models capture global pose but cannot represent the non-rigid surface dynamics of clothing and soft tissue. Generic scene flow estimates dense motion but breaks down on articulated bodies, where pixel-level supervision is also intractable to acquire. We