Domain Intersection and Domain Difference

TL;DR

This paper introduces a novel method to extract shared and unique content between two visual domains, enabling domain mapping and image generation of their intersection and union without having seen such samples during training.

Contribution

The method uniquely recovers shared and domain-specific content, allowing flexible image translation and generation of domain intersections and unions without prior examples.

Findings

Outperforms existing methods in experiments

Enables generation of images from domain intersection and union

Provides analytical proof of method constraints

Abstract

We present a method for recovering the shared content between two visual domains as well as the content that is unique to each domain. This allows us to map from one domain to the other, in a way in which the content that is specific for the first domain is removed and the content that is specific for the second is imported from any image in the second domain. In addition, our method enables generation of images from the intersection of the two domains as well as their union, despite having no such samples during training. The method is shown analytically to contain all the sufficient and necessary constraints. It also outperforms the literature methods in an extensive set of experiments. Our code is available at https://github.com/sagiebenaim/DomainIntersectionDifference.