MDT: Unsupervised Multi-Domain Image-to-Image Translator Based on Generative Adversarial Networks

In recent years, many methods have been proposed to tackle unsupervised image-to-image translation. However, they mainly focus on two-domain scenarios. To address issues like large cost of training time and resources in translation across multiple (more than two) number of domains, we propose an unsupervised method based on generative adversarial networks. Our method has only one encoder for the consideration of efficiency, together with several domain-specified decoders to transform an image into multiple domains without needing an input domain label. In addition, we propose to employ two constraints namely reconstruction loss and identity loss to further improve the generation. We conduct experiments on two datasets. The results demonstrate the effectiveness and efficiency of our proposed method against state-of-the-art methods.