Generative Choreography using Deep Learning
This work addresses the need for AI-assisted creative tools in dance choreography, offering a collaborative system for choreographers, though it is incremental in applying existing deep learning methods to this domain.
The paper tackles the problem of generating novel choreographic material in the style of a specific choreographer, achieving promising results in producing compositional cohesion beyond simple movement sequences.
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.