发表机构
Monash University（莫纳什大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对现有群体舞蹈生成模型受固定群体规模限制的问题，提出ChainDance框架，通过舞者链分解与轻量级模块实现可变规模群体舞蹈生成，参数与训练成本显著降低且性能更优。
AI 中文摘要
群体舞蹈生成旨在从音乐中合成协调的多舞者编舞，广泛应用于动画和交互式内容创作领域。该任务需要建模密集的人际依赖关系以确保空间协调，同时自然保留每个舞者的身份。现有方法采用端到端Transformer联合建模所有舞者，这使得架构与固定群体规模绑定，并在帧间纠缠每个舞者的身份。我们提出ChainDance，这是一个可扩展的框架，将群体舞蹈生成重新表述为舞者链：对每个舞者的条件分布进行顺序分解，允许单个模型在不重新训练的情况下扩展到可变群体规模，并自然保留每个舞者的身份。ChainDance构建在冻结的单舞者扩散骨干之上，引入了两个轻量级模块：用于每个舞者语义条件的角色感知文本编码器（RATE），以及通过距离加权图卷积网络聚合先前生成舞者的群体感知运动编码器（GAME），并在推理时引入无需训练的噪声优化过程以强制执行全局空间一致性。在AIOZ-GDance数据集上的实验表明，与现有方法相比，ChainDance在结构上保留每个舞者身份的同时，实现了最先进的运动质量和群体协调性，参数减少3-4倍，训练时间减少3-6倍。
英文摘要
Group dance generation aims to synthesize coordinated multi-dancer choreography from music, with broad applications in animation and interactive content creation. This task requires modeling dense inter-person dependencies to ensure spatial coordination, while naturally preserving individual dancer identities. Existing approaches model all dancers jointly with end-to-end transformers, which tie the architecture to a fixed group size and entangle per-dancer identities across frames. We propose ChainDance, a scalable framework that reformulates group dance generation as a Chain-of-Dancers: a sequential decomposition over per-dancer conditional distributions, allowing a single model to scale across variable group sizes without retraining and naturally preserving per-dancer identity. Built on a frozen single-dancer diffusion backbone, ChainDance introduces two lightweight modules: a Role-Aware Text Encoder (RATE) for per-dancer semantic conditioning, and a Group-Aware Motion Encoder (GAME) that aggregates previously generated dancers via a distance-weighted graph convolutional network, and incorporates a training-free noise optimization procedure at inference time to enforce global spatial coherence. Experiments on AIOZ-GDance demonstrate that ChainDance achieves state-of-the-art motion quality and group coordination while structurally preserving per-dancer identity, with $3$-$4\times$ fewer parameters and requiring $3$-$6\times$ less training time compared to prior approaches.
CommentsAccepted at NeurIPS 2026
