MAMHOI: Factorizing Scene-Aware Human-Object Interaction through Affordances

Key points

• Human-scene datasets provide rich information about environment-aware motion, while human-object datasets capture detailed interaction dynamics, yet paired human-object-scene data remain scarce.1
• We present MAMHOI, an affordance-mediated factorization for scene-aware human-object interaction generation.1
• MAMHOI factorizes scene-aware HOI generation through an explicit motion-affordance interface between scene understanding and motion synthesis: a scene-conditioned model first predicts where and how an interaction can be feasibly executed, and an affordance-conditioned HOI model then generates the corresponding human-object motion.1
• Experiments in complex indoor environments show that MAMHOI reduces object--scene penetration while better preserving human--object interaction quality, yielding more realistic and physically feasible scene-aware interactions.1

Sources (1)

• [1]MAMHOI: Factorizing Scene-Aware Human-Object Interaction through Affordances
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 05:52 PM

  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.

  Human-scene datasets provide rich information about environment-aware motion, while human-object datasets capture detailed interaction dynamics, yet paired human-object-scene data remain scarce.

Extractive summary: sentences quoted from the sources.