ChoreoNet: Towards Music to Dance Synthesis with Choreographic Action Unit

TL;DR

ChoreoNet is a novel two-stage framework for music-to-dance synthesis that mimics human choreography by predicting choreographic units and then generating continuous dance motions, outperforming baseline methods.

Contribution

The paper introduces a two-stage music-to-dance synthesis framework and constructs a dataset to incorporate choreographic knowledge, advancing the realism and coherence of generated dance motions.

Findings

ChoreoNet achieves higher CAU BLEU scores than baselines.

The framework produces more rhythmically and emotionally aligned dance motions.

User studies favor ChoreoNet's generated dances over existing methods.

Abstract

Dance and music are two highly correlated artistic forms. Synthesizing dance motions has attracted much attention recently. Most previous works conduct music-to-dance synthesis via directly music to human skeleton keypoints mapping. Meanwhile, human choreographers design dance motions from music in a two-stage manner: they firstly devise multiple choreographic dance units (CAUs), each with a series of dance motions, and then arrange the CAU sequence according to the rhythm, melody and emotion of the music. Inspired by these, we systematically study such two-stage choreography approach and construct a dataset to incorporate such choreography knowledge. Based on the constructed dataset, we design a two-stage music-to-dance synthesis framework ChoreoNet to imitate human choreography procedure. Our framework firstly devises a CAU prediction model to learn the mapping relationship between music and CAU sequences. Afterwards, we devise a spatial-temporal inpainting model to convert the CAU sequence into continuous dance motions. Experimental results demonstrate that the proposed ChoreoNet outperforms baseline methods (0.622 in terms of CAU BLEU score and 1.59 in terms of user study score).