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

arXiv: https://arxiv.org/abs/2507.21518 · HTML: https://mlsanity.com/paper/2507.21518/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 40 references that are in the map.
- First posted on arXiv 29 Jul 2025.

## Builds on (most cited first, 24 of 24)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [AI Choreographer: Music Conditioned 3D Dance Generation with AIST++](https://mlsanity.com/paper/2101.08779/) (2021)
- [SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers](https://mlsanity.com/paper/2410.10629/) (2024)
- [EDGE: Editable Dance Generation From Music](https://mlsanity.com/paper/2211.10658/) (2022)
- [A Spatio-temporal Transformer for 3D Human Motion Prediction](https://mlsanity.com/paper/2004.08692/) (2020)
- [Human Motion Generation: A Survey](https://mlsanity.com/paper/2307.10894/) (2023)
- [FineDance: A Fine-grained Choreography Dataset for 3D Full Body Dance Generation](https://mlsanity.com/paper/2212.03741/) (2022)
- [Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives](https://mlsanity.com/paper/2403.10518/) (2024)
- [Motion Anything: Any to Motion Generation](https://mlsanity.com/paper/2503.06955/) (2025)
- [Music-Driven Group Choreography](https://mlsanity.com/paper/2303.12337/) (2023)
- [Learning to dance: A graph convolutional adversarial network to generate realistic dance motions from audio](https://mlsanity.com/paper/2011.12999/) (2020)
- [DiffDance: Cascaded Human Motion Diffusion Model for Dance Generation](https://mlsanity.com/paper/2308.02915/) (2023)
- [Weakly Supervised Deep Recurrent Neural Networks for Basic Dance Step Generation](https://mlsanity.com/paper/1807.01126/) (2018)
- [Dance Style Transfer with Cross-modal Transformer](https://mlsanity.com/paper/2208.09406/) (2022)
- [Audio Generation with Multiple Conditional Diffusion Model](https://mlsanity.com/paper/2308.11940/) (2023)
- [Dance with You: The Diversity Controllable Dancer Generation via Diffusion Models](https://mlsanity.com/paper/2308.13551/) (2023)
- [Controllable Group Choreography using Contrastive Diffusion](https://mlsanity.com/paper/2310.18986/) (2023)
- [Graph-based Normalizing Flow for Human Motion Generation and Reconstruction](https://mlsanity.com/paper/2104.03020/) (2021)
- [When Creators Meet the Metaverse: A Survey on Computational Arts](https://mlsanity.com/paper/2111.13486/) (2021)
- [An Extensive Review of Computational Dance Automation Techniques and Applications](https://mlsanity.com/paper/1906.00606/) (2019)

## Built on by (most cited first, 1 of 1)

- [ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreography](https://mlsanity.com/paper/2603.22316/) (2026)

## Abstract (arXiv)

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/.