Scalable Group Choreography via Variational Phase Manifold Learning

TL;DR

This paper introduces a scalable, phase-based variational generative model for group dance motion that maintains naturalness and synchronization, outperforming existing methods and supporting an unlimited number of dancers with minimal memory.

Contribution

We propose a novel variational phase manifold learning approach that enables scalable, high-fidelity group dance generation with unlimited dancers, overcoming dataset limitations.

Findings

Outperforms recent state-of-the-art methods significantly.

Supports generation of an unlimited number of dancers.

Maintains naturalness and synchronization in group dance motion.

Abstract

Generating group dance motion from the music is a challenging task with several industrial applications. Although several methods have been proposed to tackle this problem, most of them prioritize optimizing the fidelity in dancing movement, constrained by predetermined dancer counts in datasets. This limitation impedes adaptability to real-world applications. Our study addresses the scalability problem in group choreography while preserving naturalness and synchronization. In particular, we propose a phase-based variational generative model for group dance generation on learning a generative manifold. Our method achieves high-fidelity group dance motion and enables the generation with an unlimited number of dancers while consuming only a minimal and constant amount of memory. The intensive experiments on two public datasets show that our proposed method outperforms recent state-of-the-art approaches by a large margin and is scalable to a great number of dancers beyond the training data.