PAMI: Part Anchored Motion for Text to Human-Object Interaction Generation
Text-conditioned full-body human-object interaction (HOI) generation requires synthesizing human motion and object trajectories that match the input text while remaining precisely coordinated over time.
ProofPaper ↗
Key points
- Most methods represent the human and object as separate trajectories and predict the global human-object couplings.
- We introduce PAMI, a Part-Anchored Motion framework for Interaction generation.
- Inspired by the classic Hough Transform, our key idea is to localize object motion by letting body-part anchors vote for it: we express object motion relative to multiple body-part anchors and use PamiVAE to learn an interaction latent space, decoding frame-wise weights that aggregate these part-specific votes.
- PamiGen first generates a coarse human-object interaction from text in this structured latent space, and PamiRefiner then recursively resolves fine-grained contact geometry using a hybrid surface-sensing representation, combining long-range probes that capture overall body-part influence with short-range sensors that resolve detailed contacts near the object surface.
Sources (1)
- [1]PAMI: Part Anchored Motion for Text to Human-Object Interaction GenerationHugging Face Daily Papers · Sep 29, 12:00 AM
Text-conditioned full-body human-object interaction (HOI) generation requires synthesizing human motion and object trajectories that match the input text while remaining precisely coordinated over time.
Most methods represent the human and object as separate trajectories and predict the global human-object couplings.
Extractive summary: sentences quoted from the sources.
