39 datasets found

The dataset used in the paper for image denoising and image restoration tasks.

The Restore Dataset is a benchmark for general image restoration, containing 8000 images with various degradations.

Cryo-CARE: a method for content-aware image restoration for cryo-transmission electron microscopy data

Validation set for image restoration

A large-scale dataset for descanning, which is the process of restoring original images from scanned copies.

WebPhoto dataset for image restoration

A dataset for image restoration

A strong prompter for all-in-one image restoration

The dataset used in this paper for testing the 3D-RecGAN++ model. It contains 1.5k SV and 2.5k CV testing datasets for each of the 6 categories.

The dataset used in the Plug-and-Play algorithm convergence analysis.

The proposed system is composed of three neural networks (NN): an auto-regressive module (ARM) fψ, an upsampler fυ and a synthesis fθ.

The CTFilm20K dataset is a large-scale head CT film database containing approximately 20,000 pictures, with various real-world warping scenarios and different contents.

The SwinIR dataset is a benchmark for image restoration.

The dataset used in this work is a custom synthetic dataset generated using the liquid-dsp library, containing 600000 examples of each of 13.8 million examples, with SNRs...

Real-world super-resolution (RealSR) dataset by adjusting the focal length of a digital camera, and introducing the Laplacian pyramid based kernel prediction network (LP-KPN) to...

Optical coherence tomography (OCT) dataset used for denoising and image restoration.

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....

The dataset used for training and validation of the proposed approach to combine semantic segmentation and dense outlier detection.

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...