InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing

Documenti analoghi

• Move as You Say, Interact as You Can: Language-guided Human Motion Generation with Scene Affordance
  di: Wang, Zan, et al.
  Pubblicazione: (2024)
• Towards Zero-shot Human-Object Interaction Detection via Vision-Language Integration
  di: Xue, Weiying, et al.
  Pubblicazione: (2024)
• HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance
  di: Li, Lei, et al.
  Pubblicazione: (2025)
• VAGNet: Grounding 3D Affordance from Human-Object Interactions in Videos
  di: Mao, Aihua, et al.
  Pubblicazione: (2026)
• SR-Nav: Spatial Relationships Matter for Zero-shot Object Goal Navigation
  di: Fang, Leyuan, et al.
  Pubblicazione: (2026)