Compact Motion Embeddings Proposed for Unified Human Animation
A new arXiv paper introduces compact motion embeddings for feed-forward animation of a reference image using a driver's motion, capturing face, hand, and body articulation while excluding driver identity.
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-11-06 05:00 · arXiv cs.CV
Compact Motion Embeddings for Feed-forward Unified Human Animation