[2505.05589] ReactDance: Hierarchical Representation for High-Fidelity and Coherent Long-Form Reactive Dance Generation

Computer Science > Computer Vision and Pattern Recognition arXiv:2505.05589 (cs) [Submitted on 8 May 2025 (v1), last revised 5 Mar 2026 (this version, v3)] Title:ReactDance: Hierarchical Representation for High-Fidelity and Coherent Long-Form Reactive Dance Generation Authors:Jingzhong Lin, Xinru Li, Yuanyuan Qi, Bohao Zhang, Wenxiang Liu, Kecheng Tang, Wenxuan Huang, Xiangfeng Xu, Bangyan Li, Changbo Wang, Gaoqi He View a PDF of the paper titled ReactDance: Hierarchical Representation for High-Fidelity and Coherent Long-Form Reactive Dance Generation, by Jingzhong Lin and 10 other authors View PDF HTML (experimental) Abstract:Reactive dance generation (RDG), the task of generating a dance conditioned on a lead dancer's motion, holds significant promise for enhancing human-robot interaction and immersive digital entertainment. Despite progress in duet synchronization and motion-music alignment, two key challenges remain: generating fine-grained spatial interactions and ensuring long-term temporal coherence. In this work, we introduce \textbf{ReactDance}, a diffusion framework that operates on a novel hierarchical latent space to address these spatiotemporal challenges in RDG. First, for high-fidelity spatial expression and fine-grained control, we propose Hierarchical Finite Scalar Quantization (\textbf{HFSQ}). This multi-scale motion representation effectively disentangles coarse body posture from subtle limb dynamics, enabling independent and detailed control over both a...