Skip to yearly menu bar Skip to main content


Extremal Domain Translation with Neural Optimal Transport

Milena Gazdieva · Alexander Korotin · Daniil Selikhanovych · Evgeny Burnaev

Great Hall & Hall B1+B2 (level 1) #805
[ ]
[ Paper [ Poster [ OpenReview
Thu 14 Dec 3 p.m. PST — 5 p.m. PST


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

Chat is not available.