Towards Fine-Grained Control over Latent Space for Unpaired Image-to-Image Translation

Lei Luo, William H. Hsu, Shangxian Wang

Abstract: We address the open problem of unpaired image-to-image (I2I) translation using a generative model with fine-grained control over the latent space. The goal is to learn the conditional distribution of translated images given images from a source domain without access to the joint distribution. Previous works, such as MUNIT and DRIT, which simply keep content latent codes and exchange the style latent codes, generate images of inferior quality. In this paper, we propose a new framework for unpaired I2I translation. Our framework first assumes that the latent space can be decomposed into content and style sub-spaces. Instead of naively exchanging style codes when translating, our framework uses an interpolator that guides the transformation and is able to produce intermediate results under different strengths of translation. Domain specific information, which might still exist in content codes, is excluded in our framework. Extensive experiments show that the translated images using our framework are superior than or comparable to state-of-the-art baselines. Code is available upon publication.

External IDs:dblp:conf/icann/LuoHW21