Unpaired Image-to-Image Translation via Neural Schr\"odinger Bridge

arXiv:2305.15086v3 Announce Type: replace-cross
Abstract: Diffusion models are a powerful class of generative models which simulate stochastic differential equations (SDEs) to generate data from noise. While diffusion models have achieved remarkable progress, they have limitations in unpaired image-to-image (I2I) translation tasks due to the Gaussian prior assumption. Schr\"{o}dinger Bridge (SB), which learns an SDE to translate between two arbitrary distributions, have risen as an attractive solution to this problem. Yet, to our best knowledge, none of SB models so far …

arxiv bridge cs.ai cs.cv cs.lg image image-to-image image-to-image translation stat.ml translation type via