BeatDance: Generating Beat-Consistent 3D Dance with Hierarchical Spatial-Temporal Modeling

arXiv:2609.37400 · cs.CV · Submitted 2026-09-29 · Read on arXiv

cs.CV

Submitted: 2026-09-29

Updated: 2026-09-29

Comments: Published in Pattern Recognition

Journal ref: Pattern Recognition, Volume 180, 114344 (2026)

DOI: 10.1016/j.patcog.2026.114344

Project page: https://shenxiaojian.github.io/BeatDance

License: http://creativecommons.org/licenses/by-nc-nd/4.0/

The gist: Generating realistic 3D dance from music is a challenging task that requires accurate synchronization with musical rhythms while capturing the spatial complexity of human motion.

Terminology

Abstract

Generating realistic 3D dance from music is a challenging task that requires accurate synchronization with musical rhythms while capturing the spatial complexity of human motion. Although existing methods can generate physically plausible dance motions, they often struggle to achieve precise alignment with music, such as the beat. To address this limitation, we propose a novel diffusion-based framework, BeatDance, with two components: 1) We present a Hierarchical Decoupled Attention (HDA) module, which first disentangles the learning of human pose and temporal dynamics. A hierarchical structure is then employed to capture both short-term and long-term dependencies, thereby enhancing spatial-temporal modeling. 2) We adopt cycle-consistent learning by introducing an auxiliary dance-to-music module. During training, discrepancies between the reconstructed and original music induce a stronger loss signal, effectively encouraging the consistency property between the music and dance motion. Extensive experimental results demonstrate that our proposed approach outperforms recent competitive methods on two benchmark datasets.

Sources

Related papers