Extremal Domain Translation with Neural Optimal Transport

01/30/2023

∙

by   Milena Gazdieva, et al.

∙

2

∙

share

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.