ChoreoStudio：音乐驱动群舞编舞中规划“什么队形、何时变换、谁来执行”
ChoreoStudio: Planning What, When, and Who in Music-Driven Group Choreography
AI 导读
arXiv 论文提出 ChoreoStudio，让音乐驱动群舞生成显式规划编舞：音乐解耦器将音频分解为帧级节奏与段级结构特征，冻结的全模态模型充当编剧生成全局语义描述，Director 据此输出队形目标、变换时机与执行者三重耦合决策。扩散生成器以帧对齐音乐特征控制身体动作并保持节拍对齐。在 AIOZ-GDance 上，ChoreoStudio 在运动质量、群体组织与队形动态方面达到 SOTA。
正文 · 原文
Abstract:Music-driven group dance generation must decide not only how each dancer moves, but also what formation the group should form, when it should change, and who should execute each transition. Existing methods can generate orderly and rhythmically synchronized group motion, but remain limited in formation evolution and inter-dancer interaction. In human choreography, formation transitions often align with changes in high-level musical structure, such as the progression from an introduction to a chorus or from a chorus to a climax. We present ChoreoStudio, which makes choreography planning explicit. A music disentangler first decomposes the audio into frame-level rhythmic features and segment-level structural features. Given the segment-level features and sparse labels, a frozen omni-modal model acts as a scriptwriter, producing a global semantic description that guides the Director's choreography planning. Based on this context, the Director produces three coupled interaction decisions: a centroid-relative point set specifies what formation to produce, a transition gate determines when it should change, and a mobility allocation indicates who should execute the transition. The transition gate and mobility allocation are further conditioned on the planned geometric change, coupling formation targets with their temporal and dancer-specific execution. At a finer temporal scale, frame-aligned music features condition the diffusion generator to control detailed body motion and preserve beat-level alignment. The segment-level interaction plan is injected in parallel through frame-aligned instruction tokens and cross-dancer attention biases, coordinating how the generator realizes each transition. Experiments on AIOZ-GDance demonstrate that ChoreoStudio follows the planned interactions while achieving state-of-the-art performance in motion quality, group organization, and formation dynamics.
| Subjects: | Sound (cs.SD); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.32325 [cs.SD] |
| (or arXiv:2610.32325v1 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32325 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jing Xu [view email]
[v1]
Fri, 23 Oct 2026 08:23:10 UTC (4,824 KB)
来源：arXiv cs.AI · arxiv.org