-
Open Image Dataset
The Open Image Dataset (OID) is a large-scale image dataset that contains a diverse set of images. -
DIV2K (1-800)
The dataset used for training and testing the proposed Multi-scale Dense Cross Network (MDCN) for image super-resolution. -
End-to-End Deep and Shallow (EEDS) networks for image super-resolution
The proposed End-to-End Deep and Shallow (EEDS) networks method for image super-resolution. -
Component Divide-and-Conquer for Real-World Image Super-Resolution
A component divide-and-conquer approach for real-world image super-resolution. -
RealSR-Nikon
A benchmark for real-world image super-resolution. -
VCISR: Blind Single Image Super-Resolution with Video Compression Synthetic Data
A video compression degradation model to synthesize low-resolution image data in the blind SISR task. -
Sun-Hays80
The dataset contains images with varying levels of degradation. -
Diffusion model with detail complement for super-resolution of remote sensing
A dataset of images for image super-resolution, including license plate images. -
Combining attention module and pixel shuffle for license plate super-resolution
A dataset of images for license plate super-resolution, including images with varying lighting conditions. -
Saudi License Plate Dataset
A dataset of Saudi license plates, both in low and high resolutions, used for training a diffusion model for license plate super-resolution. -
CelebA Face Dataset
CelebA face dataset for image super-resolution. -
Cross-Modal Super-Resolution Dataset (CMSRD)
Remote sensing images captured by different platforms exhibit significant disparities in spatial resolution. Large scale factor super-resolution (SR) algorithms are vital for... -
CNAM-CD Dataset
The CNAM-CD dataset is a multi-class change detection dataset with a resolution of 0.5 meter. -
SECOND Dataset
The SECOND dataset is a semantic change detection dataset with 7 land cover class annotations. -
Manga109 dataset
Manga109 dataset is a benchmark for Single Image Super-Resolution (SISR) tasks. It contains 109 manga images with randomly selected reference images. -
Urban100 dataset
The Urban100 dataset is a benchmark for image denoising, containing 100 images with varying levels of noise. -
BSD100 dataset
The BSD100 dataset consists of 100 images with 4x scaling.
