Unsupervised Image-to-Image Translation Networks

TLDR

Unsupervised image‑to‑image translation seeks to learn a joint distribution across domains from marginal image sets, but without extra assumptions the joint distribution is underdetermined. The study aims to resolve this ambiguity by assuming a shared latent space and proposing a Coupled GAN‑based framework. The framework employs Coupled GANs to map images into a shared latent space, enabling joint distribution learning across domains. The method achieves high‑quality translations on street scenes, animals, and faces, and attains state‑of‑the‑art domain‑adaptation performance on benchmark datasets. Code and additional results are available at https://github.com/mingyuliutw/unit.

Abstract

Unsupervised image-to-image translation aims at learning a joint distribution of images in different domains by using images from the marginal distributions in individual domains. Since there exists an infinite set of joint distributions that can arrive the given marginal distributions, one could infer nothing about the joint distribution from the marginal distributions without additional assumptions. To address the problem, we make a shared-latent space assumption and propose an unsupervised image-to-image translation framework based on Coupled GANs. We compare the proposed framework with competing approaches and present high quality image translation results on various challenging unsupervised image translation tasks, including street scene image translation, animal image translation, and face image translation. We also apply the proposed framework to domain adaptation and achieve state-of-the-art performance on benchmark datasets. Code and additional results are available in https://github.com/mingyuliutw/unit .