Unsupervised Image-to-Image Translation Using Domain-Specific Variational Information Bound

TL;DR

This paper introduces an unsupervised image-to-image translation method that captures both domain-invariant and domain-specific information by maximizing a variational information bound, enabling diverse target domain mappings.

Contribution

It proposes a novel framework that models domain-specific information in unsupervised image translation using a variational information bound, overcoming limitations of shared-latent space methods.

Findings

Enables mapping a single source image to multiple target images.

Captures domain-specific details not modeled by previous methods.

Supports diverse image generation in target domain.

Abstract

Unsupervised image-to-image translation is a class of computer vision problems which aims at modeling conditional distribution of images in the target domain, given a set of unpaired images in the source and target domains. An image in the source domain might have multiple representations in the target domain. Therefore, ambiguity in modeling of the conditional distribution arises, specially when the images in the source and target domains come from different modalities. Current approaches mostly rely on simplifying assumptions to map both domains into a shared-latent space. Consequently, they are only able to model the domain-invariant information between the two modalities. These approaches usually fail to model domain-specific information which has no representation in the target domain. In this work, we propose an unsupervised image-to-image translation framework which maximizes a domain-specific variational information bound and learns the target domain-invariant representation of the two domain. The proposed framework makes it possible to map a single source image into multiple images in the target domain, utilizing several target domain-specific codes sampled randomly from the prior distribution, or extracted from reference images.