# ST-GDance: Long-Term and Collision-Free Group Choreography from Music

Source: [ST-GDance: Long-Term and Collision-Free Group Choreography from Music](<https://www.sota2.com/research/paper/68fa7a451e209131cea82167>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:16:12.275Z

Authors: Jing Xu, Weiqiang Wang, Cunjian Chen, Jun Liu, Qiuhong Ke

Published: 2025-07-29T05:54:48.000Z

## Abstract

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/.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Group Dance Generation on AIOZ-GDance long-duration (test)](<https://www.sota2.com/research/sota/group-dance-generation-on-aioz-gdance-long-duration-test.md>): Group Dance Generation; AIOZ-GDance long-duration (test); GMR: 34.25.

- [Group Dance Generation on AIOZ-GDance short-duration](<https://www.sota2.com/research/sota/group-dance-generation-on-aioz-gdance-short-duration.md>): Group Dance Generation; AIOZ-GDance short-duration; GMR: 14.76.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2507.21518>)

[PDF](<https://arxiv.org/pdf/2507.21518.pdf>)