English

PF-D2M: A Pose-free Diffusion Model for Universal Dance-to-Music Generation

Sound 2026-01-23 v1 Computer Vision and Pattern Recognition Machine Learning Multimedia Audio and Speech Processing

Abstract

Dance-to-music generation aims to generate music that is aligned with dance movements. Existing approaches typically rely on body motion features extracted from a single human dancer and limited dance-to-music datasets, which restrict their performance and applicability to real-world scenarios involving multiple dancers and non-human dancers. In this paper, we propose PF-D2M, a universal diffusion-based dance-to-music generation model that incorporates visual features extracted from dance videos. PF-D2M is trained with a progressive training strategy that effectively addresses data scarcity and generalization challenges. Both objective and subjective evaluations show that PF-D2M achieves state-of-the-art performance in dance-music alignment and music quality.

Keywords

Cite

@article{arxiv.2601.15872,
  title  = {PF-D2M: A Pose-free Diffusion Model for Universal Dance-to-Music Generation},
  author = {Jaekwon Im and Natalia Polouliakh and Taketo Akama},
  journal= {arXiv preprint arXiv:2601.15872},
  year   = {2026}
}

Comments

4 pages, 2 figures

R2 v1 2026-07-01T09:15:38.091Z