PF-D2M: A Pose-free Diffusion Model for Universal Dance-to-Music Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909997865107456 |
|---|---|
| author | Im, Jaekwon Polouliakh, Natalia Akama, Taketo |
| author_facet | Im, Jaekwon Polouliakh, Natalia Akama, Taketo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_15872 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PF-D2M: A Pose-free Diffusion Model for Universal Dance-to-Music Generation Im, Jaekwon Polouliakh, Natalia Akama, Taketo Sound Computer Vision and Pattern Recognition Machine Learning Multimedia Audio and Speech Processing 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. |
| title | PF-D2M: A Pose-free Diffusion Model for Universal Dance-to-Music Generation |
| topic | Sound Computer Vision and Pattern Recognition Machine Learning Multimedia Audio and Speech Processing |
| url | https://arxiv.org/abs/2601.15872 |