GANspire

Hugo Scurto, Baptiste Caramiaux, 2021
web application, generative deep learning

A generative AI of breathing waveforms. It uses generative deep learning to realistically reproduce fine-grained variations of human breathing, named “personnalités ventilatoires” by pulmonologists. It relies on the Marcelle web-based toolkit to enable interactive exploration of deep latent space. GANspire is at the heart of the art-health project RÉESPIRATION and enabled the production of cultural probes for respiratory care research.

Designed collaboratively with pulmonologists.

Year
2021

Credits
The project was developed with Baptiste Caramiaux, Thomas Similowski, and Samuel Bianchini in collaboration with the HCI Sorbonne group of ISIR, the R3S department of AP-HP, and the Reflective Interaction group of EnsadLab, in the context of a postdoctoral fellowship program at Faculty of Medicine, Sorbonne Université (IUIS).

Publications
Article at CSCW 2023
Paper at NeurIPS 2021

Code
GitHub

This slideshow requires JavaScript.