Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patterns
Ronghui Li, Hongwen Zhang, Yachao Zhang, Yuxiang Zhang, Youliang, Zhang, Jie Guo, Yan Zhang, Xiu Li, Yebin Liu

TL;DR
Lodge++ is a two-stage choreography framework that generates high-quality, ultra-long, and vivid dances from music, ensuring global pattern coherence and physical plausibility through specialized modules.
Contribution
It introduces a novel two-stage generation process combining global choreography primitives with a diffusion model, along with modules for physical plausibility and genre consistency.
Findings
Rapid generation of ultra-long dances across genres
Effective preservation of complex choreography patterns
Enhanced physical plausibility of generated dances
Abstract
We propose Lodge++, a choreography framework to generate high-quality, ultra-long, and vivid dances given the music and desired genre. To handle the challenges in computational efficiency, the learning of complex and vivid global choreography patterns, and the physical quality of local dance movements, Lodge++ adopts a two-stage strategy to produce dances from coarse to fine. In the first stage, a global choreography network is designed to generate coarse-grained dance primitives that capture complex global choreography patterns. In the second stage, guided by these dance primitives, a primitive-based dance diffusion model is proposed to further generate high-quality, long-sequence dances in parallel, faithfully adhering to the complex choreography patterns. Additionally, to improve the physical plausibility, Lodge++ employs a penetration guidance module to resolve character…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHuman Motion and Animation · Human Pose and Action Recognition · Music Technology and Sound Studies
MethodsDiffusion
