Unaligned Image-to-Image Translation by Learning to Reweight

TL;DR

This paper introduces a novel method for unaligned image-to-image translation that automatically learns importance weights to improve translation quality without requiring aligned domain pairs.

Contribution

We propose an importance reweighting approach that enables effective unsupervised translation between unaligned domains, addressing a key limitation of existing methods.

Findings

Our method outperforms state-of-the-art approaches on multiple tasks.

Qualitative results show more accurate and realistic translations.

Quantitative metrics demonstrate significant improvements in translation quality.

Abstract

Unsupervised image-to-image translation aims at learning the mapping from the source to target domain without using paired images for training. An essential yet restrictive assumption for unsupervised image translation is that the two domains are aligned, e.g., for the selfie2anime task, the anime (selfie) domain must contain only anime (selfie) face images that can be translated to some images in the other domain. Collecting aligned domains can be laborious and needs lots of attention. In this paper, we consider the task of image translation between two unaligned domains, which may arise for various possible reasons. To solve this problem, we propose to select images based on importance reweighting and develop a method to learn the weights and perform translation simultaneously and automatically. We compare the proposed method with state-of-the-art image translation approaches and present qualitative and quantitative results on different tasks with unaligned domains. Extensive empirical evidence demonstrates the usefulness of the proposed problem formulation and the superiority of our method.