Rhythm is a Dancer: Music-Driven Motion Synthesis with Global Structure

TL;DR

This paper introduces a hierarchical, music-driven motion synthesis framework that generates long-term, genre-specific dance sequences synchronized with music beats, emphasizing global structure and diversity in motion.

Contribution

It presents a novel hierarchical system with pose, motif, and choreography levels, enabling global dance structure and diverse, music-controlled motion synthesis.

Findings

Effective generation of natural, consistent dance movements

Control over motion content and global dance structure

Works across various dance genres

Abstract

Synthesizing human motion with a global structure, such as a choreography, is a challenging task. Existing methods tend to concentrate on local smooth pose transitions and neglect the global context or the theme of the motion. In this work, we present a music-driven motion synthesis framework that generates long-term sequences of human motions which are synchronized with the input beats, and jointly form a global structure that respects a specific dance genre. In addition, our framework enables generation of diverse motions that are controlled by the content of the music, and not only by the beat. Our music-driven dance synthesis framework is a hierarchical system that consists of three levels: pose, motif, and choreography. The pose level consists of an LSTM component that generates temporally coherent sequences of poses. The motif level guides sets of consecutive poses to form a movement that belongs to a specific distribution using a novel motion perceptual-loss. And the choreography level selects the order of the performed movements and drives the system to follow the global structure of a dance genre. Our results demonstrate the effectiveness of our music-driven framework to generate natural and consistent movements on various dance types, having control over the content of the synthesized motions, and respecting the overall structure of the dance.