Saved in:
Bibliographic Details
Main Authors: Xu, Jing, Wang, Weiqiang, Chen, Cunjian, Liu, Jun, Ke, Qiuhong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.21518
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913965654671360
author Xu, Jing
Wang, Weiqiang
Chen, Cunjian
Liu, Jun
Ke, Qiuhong
author_facet Xu, Jing
Wang, Weiqiang
Chen, Cunjian
Liu, Jun
Ke, Qiuhong
contents 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/.
format Preprint
id arxiv_https___arxiv_org_abs_2507_21518
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ST-GDance: Long-Term and Collision-Free Group Choreography from Music
Xu, Jing
Wang, Weiqiang
Chen, Cunjian
Liu, Jun
Ke, Qiuhong
Artificial Intelligence
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/.
title ST-GDance: Long-Term and Collision-Free Group Choreography from Music
topic Artificial Intelligence
url https://arxiv.org/abs/2507.21518