25 datasets found

The dataset used for training and testing the proposed Multi-scale Dense Cross Network (MDCN) for image super-resolution.

A component divide-and-conquer approach for real-world image super-resolution.

A benchmark for real-world image super-resolution.

Remote sensing images captured by different platforms exhibit significant disparities in spatial resolution. Large scale factor super-resolution (SR) algorithms are vital for...

The CNAM-CD dataset is a multi-class change detection dataset with a resolution of 0.5 meter.

The SECOND dataset is a semantic change detection dataset with 7 land cover class annotations.

The Urban100 dataset is a benchmark for image denoising, containing 100 images with varying levels of noise.

Large scale image super-resolution is a challenging computer vision task, since vast information is missing in a highly degraded image.

The dataset used for testing the proposed Multi-scale Dense Cross Network (MDCN) for image super-resolution.

The RFL dataset contains 291 images.

Advanced diffusion models perform impressively in image super-resolution, but the high memory and computational costs hinder their deployment. Binarization, an ultra-compression...

The dataset used in the paper is a synthetic dataset for blind super-resolution, consisting of low-resolution images and their corresponding blur kernels.

The dataset consists of 100 images with varying sizes.

The Kodak lossless true color image suite is a collection of 24 images.

Real-ESRGAN+: Real-World Blind Super-Resolution with Sharpened Ground-Truths

The Flickr2K dataset is a low-resolution image dataset used for image super-resolution tasks.

Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data

The dataset used for training and testing the proposed super-resolution model.

The dataset used in the paper is a synthetic dataset for blind super-resolution, consisting of low-resolution images and their corresponding blur kernels.

The dataset used in the paper is a synthetic dataset for blind super-resolution, consisting of low-resolution images and their corresponding blur kernels.