Our team of dance artists, physicists, and machine learning researchers has collectively developed several original, configurable machine-learning tools to generate novel sequences of choreography as well as tunable variations on input choreographic sequences. We use recurrent neural network and autoencoder architectures from a training dataset of movements captured as 53 three-dimensional points at each timestep. Sample animations of generated sequences and an interactive version of our model can be found at http: //www.beyondimitation.com.
@article{arxiv.1907.05297,
title = {Beyond Imitation: Generative and Variational Choreography via Machine Learning},
author = {Mariel Pettee and Chase Shimmin and Douglas Duhaime and Ilya Vidrin},
journal= {arXiv preprint arXiv:1907.05297},
year = {2019}
}
Comments
8 pages, 11 figures, presented at the 10th International Conference on Computational Creativity (ICCC 2019)