We address the problem of image translation between domains or modalities for which no
direct paired data is available (ie zero-pair translation). We propose mix and match …

Image translation methods typically aim to manipulate a set of labeled attributes (given as
supervision at training time eg domain label) while leaving the unlabeled attributes intact …

Generative adversarial networks have achieved great success in unpaired image-to-image
translation. Cycle consistency allows modeling the relationship between two distinct …

Image-to-image translation aims to learn the mapping between two visual domains. There
are two main challenges for many applications: 1) the lack of aligned training pairs and 2) …

Abstract Conditional Generative Adversarial Networks (GANs) for cross-domain image-to-
image translation have made much progress recently. Depending on the task complexity …

Unsupervised image-to-image translation tasks aim to find a mapping between a source
domain X and a target domain Y from unpaired training data. Contrastive learning for …

In image-to-image translation, each patch in the output should reflect the content of the
corresponding patch in the input, independent of domain. We propose a straightforward …

State-of-the-art image translation methods tend to struggle in an imbalanced domain setting,
where one image domain lacks richness and diversity. We introduce a new unsupervised …

We propose a novel spatially-correlative loss that is simple, efficient, and yet effective for
preserving scene structure consistency while supporting large appearance changes during …

Unsupervised image-to-image translation aims to learn the translation between two visual
domains without paired data. Despite the recent progress in image translation models, it …