19 datasets found

The Waterloo Exploration Database is a large-scale dataset for testing the generalization performance of image quality assessment models.

The dataset used for training the spatial module on multiple blind image quality assessment (BIQA) datasets.

The dataset used for training the spatial module on multiple blind image quality assessment (BIQA) datasets.

The IQA dataset is a benchmark for image quality assessment, which contains a large collection of images with varying quality.

The TID2013 database contains 3000 distorted images generated by applying 24 distortion operations at 5 levels to 25 pristine images.

The dataset used for blind image quality assessment

The CSIQ database contains 866 distorted images generated by applying 5 distortion operations at 3 ∼ 5 levels to 30 pristine images.

The dataset used for blind image quality assessment

The dataset used for blind image quality assessment

Benchmarking single-image dehazing and beyond

MUSIQ and KonIQ are datasets used for image quality and aesthetic assessment.

NIMA, TReS, and DB- are datasets used for image quality and aesthetic assessment.

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

A dataset for digital image forensics, containing 224 images.

A dataset for single image super-resolution, containing 20 algorithm submissions.

A large-scale, highly varied, perceptual similarity dataset containing 484k human judgments.

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...

Blind CT image quality assessment using DDPM-derived content and transformer-based evaluator

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....