Multi-mapping Image-to-Image Translation via Learning Disentanglement

TL;DR

This paper introduces a unified image-to-image translation model that simultaneously handles multi-modal and multi-domain translation by disentangling images into latent representations and enabling flexible manipulation.

Contribution

The proposed model uniquely combines multi-modal and multi-domain translation in a single framework through disentanglement and cross-domain translation techniques.

Findings

Outperforms state-of-the-art methods in experiments

Effectively manipulates different parts of latent representations

Achieves simultaneous multi-modal and multi-domain translation

Abstract

Recent advances of image-to-image translation focus on learning the one-to-many mapping from two aspects: multi-modal translation and multi-domain translation. However, the existing methods only consider one of the two perspectives, which makes them unable to solve each other's problem. To address this issue, we propose a novel unified model, which bridges these two objectives. First, we disentangle the input images into the latent representations by an encoder-decoder architecture with a conditional adversarial training in the feature space. Then, we encourage the generator to learn multi-mappings by a random cross-domain translation. As a result, we can manipulate different parts of the latent representations to perform multi-modal and multi-domain translations simultaneously. Experiments demonstrate that our method outperforms state-of-the-art methods.