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

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. Computationally human body animation built movement transition synthesizing a dance is challenging not only because graphs that are synchronized to the beat [5], [6], [7], or motions must be continuous, smooth and expressive the emotion [8], while more recent works use either hidden locally, but also because a dance has a meaningful global Markov models [9], or recurrent neural networks [10], [11], temporal structure [2], [3]. These methods generate motions that follow the given learning using neural networks have shown promising results audio beat, while following a specific style, but show limited in controlling articulated characters and creating arbitrary variability and lack global consistency that is dictated realistic human motions, including dance.