ReFM: Semantic-Aware Refinement Flow Model for Motion Retargeting
ReFM is proposed, a source-mesh-agnostic, energy-guided model that reformulates motion retargeting as progressive refinement and progressively refines an initialized target motion through a learned flow guided by semantic consistency, physical plausibility, temporal coherence, and minimal motion modification.
Jing-Xiang Qu, Lucie Taglienti, Evan Atherton
· 0 citations