CoheDancers: Enhancing Interactive Group Dance Generation through Music-Driven Coherence Decomposition

TL;DR

CoheDancers is a novel framework that significantly improves the coherence and quality of group dance generation driven by music, using innovative strategies and a comprehensive dataset.

Contribution

The paper introduces CoheDancers, a new approach for music-driven group dance generation that enhances coherence through multiple strategies and provides a diverse open-source dataset for benchmarking.

Findings

Achieves state-of-the-art performance on I-Dancers and other datasets.

Effectively improves synchronization, naturalness, and fluidity of group dances.

Provides a new comprehensive dataset and evaluation metrics for the field.

Abstract

Dance generation is crucial and challenging, particularly in domains like dance performance and virtual gaming. In the current body of literature, most methodologies focus on Solo Music2Dance. While there are efforts directed towards Group Music2Dance, these often suffer from a lack of coherence, resulting in aesthetically poor dance performances. Thus, we introduce CoheDancers, a novel framework for Music-Driven Interactive Group Dance Generation. CoheDancers aims to enhance group dance generation coherence by decomposing it into three key aspects: synchronization, naturalness, and fluidity. Correspondingly, we develop a Cycle Consistency based Dance Synchronization strategy to foster music-dance correspondences, an Auto-Regressive-based Exposure Bias Correction strategy to enhance the fluidity of the generated dances, and an Adversarial Training Strategy to augment the naturalness of the group dance output. Collectively, these strategies enable CohdeDancers to produce highly coherent group dances with superior quality. Furthermore, to establish better benchmarks for Group Music2Dance, we construct the most diverse and comprehensive open-source dataset to date, I-Dancers, featuring rich dancer interactions, and create comprehensive evaluation metrics. Experimental evaluations on I-Dancers and other extant datasets substantiate that CoheDancers achieves unprecedented state-of-the-art performance. Code will be released.