Music-Driven Group Choreography

TL;DR

This paper introduces a large-scale dataset and a new method for generating group dance choreography from music, addressing the challenge of creating coordinated group movements in dance synthesis.

Contribution

The paper presents AIOZ-GDANCE, the first large-scale dataset for group dance, and a novel semi-autonomous labeling method, along with an effective generation technique for group choreography.

Findings

The dataset covers 7 dance styles and 16 music genres with 16.7 hours of data.

Naive single dance methods produce inconsistent group dance movements.

The proposed method outperforms baseline approaches in generating coherent group choreography.

Abstract

Music-driven choreography is a challenging problem with a wide variety of industrial applications. Recently, many methods have been proposed to synthesize dance motions from music for a single dancer. However, generating dance motion for a group remains an open problem. In this paper, we present $\rm AIOZ-GDANCE$, a new large-scale dataset for music-driven group dance generation. Unlike existing datasets that only support single dance, our new dataset contains group dance videos, hence supporting the study of group choreography. We propose a semi-autonomous labeling method with humans in the loop to obtain the 3D ground truth for our dataset. The proposed dataset consists of 16.7 hours of paired music and 3D motion from in-the-wild videos, covering 7 dance styles and 16 music genres. We show that naively applying single dance generation technique to creating group dance motion may lead to unsatisfactory results, such as inconsistent movements and collisions between dancers. Based on our new dataset, we propose a new method that takes an input music sequence and a set of 3D positions of dancers to efficiently produce multiple group-coherent choreographies. We propose new evaluation metrics for measuring group dance quality and perform intensive experiments to demonstrate the effectiveness of our method. Our project facilitates future research on group dance generation and is available at: https://aioz-ai.github.io/AIOZ-GDANCE/