HOI-PAGE creates realistic 4D human-object interactions from text by using LLM-derived part affordance graphs to guide object decomposition, reference video extraction, and constraint-based motion optimization in zero-shot fashion.
Perception encoder: The best visual embeddings are not at the output of the net- work
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance
HOI-PAGE creates realistic 4D human-object interactions from text by using LLM-derived part affordance graphs to guide object decomposition, reference video extraction, and constraint-based motion optimization in zero-shot fashion.