Unpaired multimodal image-to-image translation is a task of translating a given image in a source domain into diverse images in the target domain, overcoming the limitation of one-to-one mapping. Existing multimodal translation models are mainly based on the disentangled representations with an image reconstruction loss. We propose two approaches to improve multimodal translation quality. First, we use a content representation from the source domain conditioned on a style representation from the target domain. Second, rather than using a typical image reconstruction loss, we design MILO (Mutual Information LOss), a new stochastically-defined loss function based on information theory. This loss function directly reflects the interpretation of latent variables as a random variable. We show that our proposed model Mutual Information with StOchastic Style Representation(MISO) achieves state-of-the-art performance through extensive experiments on various real-world datasets.
@article{arxiv.1902.03938,
title = {MISO: Mutual Information Loss with Stochastic Style Representations for Multimodal Image-to-Image Translation},
author = {Sanghyeon Na and Seungjoo Yoo and Jaegul Choo},
journal= {arXiv preprint arXiv:1902.03938},
year = {2019}
}