EDIT: Exemplar-Domain Aware Image-to-Image Translation

TL;DR

The paper introduces EDIT, a novel GAN for multi-domain, exemplar-aware image-to-image translation that produces diverse, controllable stylized images while preserving content, demonstrating superior performance over existing methods.

Contribution

The paper proposes a unified generator architecture with shared and exemplar-specific parameters for flexible multi-domain image translation.

Findings

Effective multi-domain translation demonstrated.

Outperforms state-of-the-art methods quantitatively.

Produces diverse, controllable stylized images.

Abstract

Image-to-image translation is to convert an image of the certain style to another of the target style with the content preserved. A desired translator should be capable to generate diverse results in a controllable (many-to-many) fashion. To this end, we design a novel generative adversarial network, namely exemplar-domain aware image-to-image translator (EDIT for short). The principle behind is that, for images from multiple domains, the content features can be obtained by a uniform extractor, while (re-)stylization is achieved by mapping the extracted features specifically to different purposes (domains and exemplars). The generator of our EDIT comprises of a part of blocks configured by shared parameters, and the rest by varied parameters exported by an exemplar-domain aware parameter network. In addition, a discriminator is equipped during the training phase to guarantee the output satisfying the distribution of the target domain. Our EDIT can flexibly and effectively work on multiple domains and arbitrary exemplars in a unified neat model. We conduct experiments to show the efficacy of our design, and reveal its advances over other state-of-the-art methods both quantitatively and qualitatively.