Intentional Choreography with Semi-Supervised Recurrent VAEs

TL;DR

PirouNet is a semi-supervised recurrent VAE that generates choreographed dance sequences conditioned on limited labeled data, enabling style-specific dance synthesis with minimal supervision.

Contribution

Introduces PirouNet, a semi-supervised recurrent VAE that generates dance sequences conditioned on small labeled datasets, advancing dance synthesis methods.

Findings

Successfully generates choreographic sequences in specific styles.

Operates effectively with limited labeled data.

Demonstrates style-specific dance generation.

Abstract

We summarize the model and results of PirouNet, a semi-supervised recurrent variational autoencoder. Given a small amount of dance sequences labeled with qualitative choreographic annotations, PirouNet conditionally generates dance sequences in the style of the choreographer.