24 datasets found

The zebra-horse translation dataset is used to demonstrate the effectiveness of the proposed ReLGAN architecture.

The dataset used in the paper is not explicitly described. However, it is mentioned that the authors reformulated Isola's model within a brand-new geometrical framework and...

Generating artistic portraits is a challenging problem in computer vision. Existing portrait stylization models that generate good quality results are based on Image-to-Image...

A dataset of paired style and content images used for customizing a pre-trained text-to-image model with a single image pair.

A dataset used for fine-grained appearance transfer, consisting of 400 pairs of high-quality source and target images, and 100 real-world images with related source and target...

The Synthia dataset is a large-scale urban scene understanding dataset, containing 9000 samples. It is used for semantic segmentation tasks.

Pix2pixGAN is a generative adversarial network for image-to-image translation.

Image fusion aims to combine information from different source images to create a comprehensively representative image. Existing fusion methods are typically helpless in dealing...

Multimodal unsupervised image-to-image translation.

The proposed Masked Regression (MR) method for facial expression synthesis using local receptive fields.

Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks

The dataset used for unpaired image-to-image translation tasks

The Monet2Photo dataset contains images of paintings by Claude Monet.

The Skull2Animal dataset contains unpaired images of skulls and living animals. These images were curated through a process wherein skull photographs, taken by a private...

The FFHQ-Aging dataset is a facial aging dataset that contains images of faces from the FFHQ dataset, labeled with age, gender, and semantic segmentation.

A dataset of paired map and aerial images, used to train a Pix2Pix model for image-to-image translation.

Unsupervised image-to-image translation networks.

LAION-Aesthetics 6.5+ dataset contains 625K image-text pairs.

A dataset for image-to-image translation using generative adversarial networks.

The dataset used for the experiments with the proposed approach to augment image data for semantic segmentation networks by applying image-to-image translation with both, a...