PirouNet: Creating Dance through Artist-Centric Deep Learning

TL;DR

PirouNet is a semi-supervised deep learning model that enables choreographers to generate dance sequences aligned with their creative intent using minimal labeled data and subjective labels.

Contribution

It introduces a novel semi-supervised conditional recurrent variational autoencoder tailored for dance creation, allowing subjective labeling and generation with limited annotated data.

Findings

PirouNet effectively generates choreography based on subjective labels.

The model requires only about 1% labeled data for training.

Qualitative and quantitative evaluations validate its usefulness for choreographers.

Abstract

Using Artificial Intelligence (AI) to create dance choreography with intention is still at an early stage. Methods that conditionally generate dance sequences remain limited in their ability to follow choreographer-specific creative direction, often relying on external prompts or supervised learning. In the same vein, fully annotated dance datasets are rare and labor intensive. To fill this gap and help leverage deep learning as a meaningful tool for choreographers, we propose "PirouNet", a semi-supervised conditional recurrent variational autoencoder together with a dance labeling web application. PirouNet allows dance professionals to annotate data with their own subjective creative labels and subsequently generate new bouts of choreography based on their aesthetic criteria. Thanks to the proposed semi-supervised approach, PirouNet only requires a small portion of the dataset to be labeled, typically on the order of 1%. We demonstrate PirouNet's capabilities as it generates original choreography based on the "Laban Time Effort", an established dance notion describing intention for a movement's time dynamics. We extensively evaluate PirouNet's dance creations through a series of qualitative and quantitative metrics, validating its applicability as a tool for choreographers.