Generative Choreography using Deep Learning

TL;DR

This paper introduces chor-rnn, a deep learning system that generates novel dance choreography in a specific choreographer's style, enhancing creative possibilities and compositional cohesion.

Contribution

It presents a deep recurrent neural network trained on motion capture data to produce stylistically consistent and cohesive dance sequences, advancing AI-assisted choreography.

Findings

Generates dance sequences in a specific choreographer's style.

Produces higher-level compositional cohesion.

Useful for collaborative choreography and inspiration.

Abstract

Recent advances in deep learning have enabled the extraction of high-level features from raw sensor data which has opened up new possibilities in many different fields, including computer generated choreography. In this paper we present a system chor-rnn for generating novel choreographic material in the nuanced choreographic language and style of an individual choreographer. It also shows promising results in producing a higher level compositional cohesion, rather than just generating sequences of movement. At the core of chor-rnn is a deep recurrent neural network trained on raw motion capture data and that can generate new dance sequences for a solo dancer. Chor-rnn can be used for collaborative human-machine choreography or as a creative catalyst, serving as inspiration for a choreographer.