Extremal Domain Translation with Neural Optimal Transport. (arXiv:2301.12874v3 [cs.LG] UPDATED)

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. …

arxiv domain domains image style transfer transfer translated translation transport