MAMHOI: Factorizing Scene-Aware Human-Object Interaction through Affordances
arXiv:2610.12416v1 Announce Type: cross Abstract: Generating realistic human-object interactions (HOI) in complex 3D scenes requires two complementary capabilities: reasoning about interaction feasibility in the environment and synthesizing realistic human-object motion. However, supervision for these capabilities is rarely available jointly at scale. Human-scene datasets provide rich information about environment-aware motion, while human-object datasets capture detailed interaction dynamics,…