Informative Multimodal Unsupervised Image-to-Image Translation


Tien Tai Doan1,2, Guillaume Ghyselinck1 and Blaise Hanczar2, 1Dental Monitoring, France, 2University of Evry Val d’Essonne, France


We propose a new method of multimodal image translation, called InfoMUNIT, which is an extension of the state-of-the-art method MUNIT. Our method allows controlling the style of the generated images and improves their quality and diversity. It learns to maximize the mutual information between a subset of style code and the distribution of the output images. Experiments show that our model cannot only translate one image from the source domain to multiple images in the target domain but also explore and manipulate features of the outputs without annotation. Furthermore, it achieves a superior diversity and a competitive image quality to state-of-the-art methods in multiple image translation tasks.


Multimodal Image-to-Image Translation, Mutual Information, GANs, Manipulating Features, Disentangled Representation

Full Text  Volume 11, Number 5