用分治法生成长序列无碰撞群舞，效率更高。
ST-GDance: Long-Term and Collision-Free Group Choreography from Music
- 拆解空间与时间依赖，用轻量图卷积和稀疏注意力建模
- 在AIOZ-GDance上生成超长序列舞蹈，碰撞率显著降低
- 适合影视动画中复杂群舞自动生成，尤其看重效率的场景
从音乐生成群舞在影视、游戏和动画制作中有广泛应用。但需同步多舞者并保持空间协调性，随着舞者数量和序列长度增加，计算复杂度上升，运动碰撞风险加大。现有方法难以建模密集的空间-时间交互，导致可扩展性差且易发生多人碰撞。为此，我们提出ST-GDance框架，通过解耦空间与时间依赖，优化长时序无碰撞群舞生成。采用轻量级图卷积实现距离感知的空间建模，结合加速稀疏注意力实现高效的时间建模，显著降低计算开销，同时保证动作流畅且无碰撞。在AIOZ-GDance数据集上的实验表明，ST-GDance优于当前最优基线，尤其在生成长而连贯的群舞序列方面表现突出。
原文摘要 · Abstract (English)
Group dance generation from music has broad applications in film, gaming, and animation production. However, it requires synchronizing multiple dancers while maintaining spatial coordination. As the number of dancers and sequence length increase, this task faces higher computational complexity and a greater risk of motion collisions. Existing methods often struggle to model dense spatial-temporal interactions, leading to scalability issues and multi-dancer collisions. To address these challenges, we propose ST-GDance, a novel framework that decouples spatial and temporal dependencies to optimize long-term and collision-free group choreography. We employ lightweight graph convolutions for distance-aware spatial modeling and accelerated sparse attention for efficient temporal modeling. This design significantly reduces computational costs while ensuring smooth and collision-free interactions. Experiments on the AIOZ-GDance dataset demonstrate that ST-GDance outperforms state-of-the-art baselines, particularly in generating long and coherent group dance sequences. Project page: https://yilliajing.github.io/ST-GDance-Website/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。