Generative Motion Stylization within Canonical Motion Space

arXiv:2403.11469v1 Announce Type: new
Abstract: Stylized motion breathes life into characters. However, the fixed skeleton structure and style representation hinder existing data-driven motion synthesis methods from generating stylized motion for various characters. In this work, we propose a generative motion stylization pipeline, named MotionS, for synthesizing diverse and stylized motion on cross-structure characters using cross-modality style prompts. Our key insight is to embed motion style into a cross-modality latent space and perceive the cross-structure skeleton topologies, allowing for motion stylization …

abstract arxiv canonical characters cs.cv cs.gr data data-driven diverse generative hinder however life pipeline representation space style synthesis type work