Extremal Domain Translation with Neural Optimal Transport
Milena Gazdieva, Alexander Korotin, Daniil Selikhanovych, Evgeny Burnaev
Abstract
In many unpaired image domain translation problems, e.g., style transfer or super-resolution, it is important to keep the translated image similar to its respective input image. We propose the extremal transport (ET) which is a mathematical formalization of the theoretically best possible unpaired translation between a pair of domains w.r.t. the given similarity function. Inspired by the recent advances in neural optimal transport (OT), we propose a scalable algorithm to approximate ET maps as a limit of partial OT maps. We test our algorithm on toy examples and on the unpaired image-to-image translation task. The code is publicly available at https://github.com/milenagazdieva/ExtremalNeuralOptimalTransport
BibTeX
@inproceedings{
gazdieva2023extremal,
title={Extremal Domain Translation with Neural Optimal Transport},
author={Milena Gazdieva and Alexander Korotin and Daniil Selikhanovych and Evgeny Burnaev},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023},
url={https://openreview.net/forum?id=vZRiMjo826}
}