Abstract Generative Adversarial Networks (GANs) have been extremely successful in
various application domains such as computer vision, medicine, and natural language …

Supervised image-to-image translation has been proven to generate realistic images with
sharp details and to have good quantitative performance. Such methods are trained on a …

Score-based diffusion models (SBDMs) have achieved the SOTA FID results in unpaired
image-to-image translation (I2I). However, we notice that existing methods totally ignore the …

Perceiving the similarity between images has been a long-standing and fundamental
problem underlying various visual generation tasks. Predominant approaches measure the …

Recently, contrastive learning-based image translation methods have been proposed, which
contrasts different spatial locations to enhance the spatial correspondence. However, the …

Unpaired image-to-image (I2I) translation often requires to maximize the mutual information
between the source and the translated images across different domains, which is critical for …