English

Harmonious Group Choreography with Trajectory-Controllable Diffusion

Computer Vision and Pattern Recognition 2025-02-07 v4

Abstract

Creating group choreography from music is crucial in cultural entertainment and virtual reality, with a focus on generating harmonious movements. Despite growing interest, recent approaches often struggle with two major challenges: multi-dancer collisions and single-dancer foot sliding. To address these challenges, we propose a Trajectory-Controllable Diffusion (TCDiff) framework, which leverages non-overlapping trajectories to ensure coherent and aesthetically pleasing dance movements. To mitigate collisions, we introduce a Dance-Trajectory Navigator that generates collision-free trajectories for multiple dancers, utilizing a distance-consistency loss to maintain optimal spacing. Furthermore, to reduce foot sliding, we present a footwork adaptor that adjusts trajectory displacement between frames, supported by a relative forward-kinematic loss to further reinforce the correlation between movements and trajectories. Experiments demonstrate our method's superiority.

Cite

@article{arxiv.2403.06189,
  title  = {Harmonious Group Choreography with Trajectory-Controllable Diffusion},
  author = {Yuqin Dai and Wanlu Zhu and Ronghui Li and Zeping Ren and Xiangzheng Zhou and Jixuan Ying and Jun Li and Jian Yang},
  journal= {arXiv preprint arXiv:2403.06189},
  year   = {2025}
}
R2 v1 2026-06-28T15:14:56.603Z