arXiv Open Access 2026

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

Jaekwon Im Natalia Polouliakh Taketo Akama
Lihat Sumber

Abstrak

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.

Penulis (3)

J

Jaekwon Im

N

Natalia Polouliakh

T

Taketo Akama

Format Sitasi

Im, J., Polouliakh, N., Akama, T. (2026). PF-D2M: A Pose-free Diffusion Model for Universal Dance-to-Music Generation. https://arxiv.org/abs/2601.15872

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2026
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓