28 datasets found

The proposed End-to-End Deep and Shallow (EEDS) networks method for image super-resolution.

The dataset contains images with varying levels of degradation.

CelebA face dataset for image super-resolution.

The DIV2K 3× dataset is used for training and evaluation of the proposed NCNet model.

Manga109 dataset is a benchmark for Single Image Super-Resolution (SISR) tasks. It contains 109 manga images with randomly selected reference images.

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

The BSD100 dataset consists of 100 images with 4x scaling.

Single image super-resolution (SR) is the process of infer-

The Ntire 2017 challenge on single image super-resolution: Methods and results.

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

The div2k dataset contains 1000 2K-resolution images for single-image super-resolution.

Change Detection (CD) is an important problem in remote sensing in which our goal is to identify relevant changes in bi-temporal remote sensing images that can help in various...

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 CelebAHQ dataset was used with a box-downsampling operator [11].

LSUN Tower dataset is a subset of the LSUN dataset, with 708,264 images.

LSUN Dining Room dataset is a subset of the LSUN dataset, with 657,571 images.

The authors present a photorealistic text-to-image diffusion model with deep language understanding.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used DIV2K, OST, FFHQ, and CeleA-HQ datasets.

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

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