ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreography

• URL: http://arxiv.org/abs/2603.22316v1
• Date: Fri, 20 Mar 2026 04:16:31 GMT
• Title: ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreography
• Abstract summary: Group dance generation from music requires synchronizing multiple dancers while maintaining spatial coordination.<n>Recent group dance generation models have achieved promising generation quality, but they remain difficult to deploy in interactive scenarios.<n>We propose ST-GDance++, a scalable framework that decouples spatial and temporal dependencies to enable efficient and collision-aware group choreography generation.
• Score: 36.45013779800946
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Group dance generation from music requires synchronizing multiple dancers while maintaining spatial coordination, making it highly relevant to applications such as film production, gaming, and animation. Recent group dance generation models have achieved promising generation quality, but they remain difficult to deploy in interactive scenarios due to bidirectional attention dependencies. As the number of dancers and the sequence length increase, the attention computation required for aligning music conditions with motion sequences grows quadratically, leading to reduced efficiency and increased risk of motion collisions. Effectively modeling dense spatial-temporal interactions is therefore essential, yet existing methods often struggle to capture such complexity, resulting in limited scalability and unstable multi-dancer coordination. To address these challenges, we propose ST-GDance++, a scalable framework that decouples spatial and temporal dependencies to enable efficient and collision-aware group choreography generation. For spatial modeling, we introduce lightweight distance-aware graph convolutions to capture inter-dancer relationships while reducing computational overhead. For temporal modeling, we design a diffusion noise scheduling strategy together with an efficient temporal-aligned attention mask, enabling stream-based generation for long motion sequences and improving scalability in long-duration scenarios. Experiments on the AIOZ-GDance dataset show that ST-GDance++ achieves competitive generation quality with significantly reduced latency compared to existing methods.

Related papers

• Forecasting as Rendering: A 2D Gaussian Splatting Framework for Time Series Forecasting [79.37674445572462]
  Time series forecasting (TSF) remains a challenging problem due to the intricate entanglement of intraperiod-fluctuations and interperiod-trends.<n>Treating reshaped tensors as static images results in a topological mismatch.<n> relying on uniform fixed-size representations allocates modeling capacity inefficiently.<n>TimeGS is a novel framework that fundamentally shifts the forecasting paradigm from regression to 2D generative rendering.
  arXiv  Detail & Related papers  (2026-02-10T14:13:36Z)
• Towards Robust and Generalizable Continuous Space-Time Video Super-Resolution with Events [71.2439653098351]
  Continuous space-time video super-STVSR has garnered increasing interest for its capability to reconstruct high-resolution and high-frame-rate videos at arbitrary temporal scales.<n>We present EvEnhancer, a novel approach that marries unique properties of high temporal and high dynamic range encapsulated in event streams.<n>Our method achieves state-of-the-art performance on both synthetic and real-world datasets, while maintaining generalizability at OOD scales.
  arXiv  Detail & Related papers  (2025-10-04T15:23:07Z)
• ST-GDance: Long-Term and Collision-Free Group Choreography from Music [40.600668304004344]
  Group dance generation from music has broad applications in film, gaming, and animation production.<n>We propose ST-GDance, a novel framework that decouples spatial and temporal dependencies to optimize long-term and collision-free group choreography.
  arXiv  Detail & Related papers  (2025-07-29T05:54:48Z)
• TCDiff++: An End-to-end Trajectory-Controllable Diffusion Model for Harmonious Music-Driven Group Choreography [28.058589813506483]
  TCDiff++ is a music-driven end-to-end framework designed to generate harmonious group dance.<n>To mitigate multi-dancer collisions, we utilize a dancer positioning embedding to encode temporal and identity information.<n>To address the issue of single-dancer foot sliding, we introduce a swap mode embedding to indicate dancer swapping patterns.
  arXiv  Detail & Related papers  (2025-06-23T14:15:20Z)
• MotionRAG-Diff: A Retrieval-Augmented Diffusion Framework for Long-Term Music-to-Dance Generation [10.203209816178552]
  MotionRAG-Diff is a hybrid framework that integrates Retrieval-Augmented Generation and diffusion-based refinement.<n>Our method introduces three core innovations.<n>It achieves state-of-the-art performance in motion quality, diversity, and music-motion synchronization accuracy.
  arXiv  Detail & Related papers  (2025-06-03T09:12:48Z)
• ReactDance: Hierarchical Representation for High-Fidelity and Coherent Long-Form Reactive Dance Generation [21.732021702335345]
  We introduce textbfReactDance, a diffusion framework that operates on a novel hierarchical latent space.<n>We show that ReactDance substantially outperforms state-of-the-art methods in motion quality, long-term coherence, and sampling efficiency.
  arXiv  Detail & Related papers  (2025-05-08T18:42:38Z)
• Lagrangian Motion Fields for Long-term Motion Generation [51.02126882968116]
  We introduce the concept of Lagrangian Motion Fields, specifically designed for long-term motion generation.<n>By treating each joint as a Lagrangian particle with uniform velocity over short intervals, our approach condenses motion representations into a series of "supermotions"<n>Our solution is versatile and lightweight, eliminating the need for neural network preprocessing.
  arXiv  Detail & Related papers  (2024-09-03T01:38:06Z)
• LongDanceDiff: Long-term Dance Generation with Conditional Diffusion Model [3.036230795326545]
  LongDanceDiff is a conditional diffusion model for sequence-to-sequence long-term dance generation. It addresses the challenges of temporal coherency and spatial constraint. We also address common visual quality issues in dance generation, such as foot sliding and unsmooth motion.
  arXiv  Detail & Related papers  (2023-08-23T06:37:41Z)
• DiffDance: Cascaded Human Motion Diffusion Model for Dance Generation [89.50310360658791]
  We present a novel cascaded motion diffusion model, DiffDance, designed for high-resolution, long-form dance generation. This model comprises a music-to-dance diffusion model and a sequence super-resolution diffusion model. We demonstrate that DiffDance is capable of generating realistic dance sequences that align effectively with the input music.
  arXiv  Detail & Related papers  (2023-08-05T16:18:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.