11 datasets found

The dataset used for training the StyleGAN2-ADA algorithm consists of high-resolution spatial data.

Real-time semantic segmentation system for high-resolution images

PEOPLE2K contain about 4846 images.

SCAPES2K contains about 13000 images with the theme of natural scenes and all images have pixel above 2048*2048 pixels.

CelebA-HQ-256 is a high-resolution dataset of 256x256 images of faces.

FloodNet is a high-resolution image dataset acquired by a small UAV platform, DJI Mavic Pro quadcopters, after Hurricane Harvey.

Flickr-Faces-HQ contains 70,000 face images at 1024 × 1024 resolution, which were originally crawled from Flickr, manually checked to discard low-quality samples, and then...

CelebAMask-HQ provides the parsing map of images in CelebA-HQ down-sampled to 512 × 512, where pixel-level annotation of 19 classes, including facial components and accessories,...

CelebAHQ is a dataset of celebrity faces, with 30,000 images of 10,000 celebrities.

Single Image Super-Resolution (SR) aims to generate a High Resolution (HR) image I SR from a low resolution (LR) im-age I LR such that it is similar to original HR image I HR....

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...