20 datasets found

The dataset used for training and testing the proposed model.

This paper uses robust statistics and curvelet transform to learn a general-purpose no-reference (NR) image quality assessment (IQA) model.

Face sketch synthesis has wide applications ranging from digital entertainments to law enforcements. Objective image quality assessment scores and face recognition accuracy are...

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 OCTA-25K-IQA-SEG dataset for image quality assessment

Four publicly available HDR-IQA datasets are adopted for benchmarking: Narwaria2013, Valenzise2014, Zerman2017, and UPIQ.

Four publicly available HDR-IQA datasets are adopted for benchmarking: Narwaria2013, Valenzise2014, Zerman2017, and UPIQ.

Four publicly available HDR-IQA datasets are adopted for benchmarking: Narwaria2013, Valenzise2014, Zerman2017, and UPIQ.

Four publicly available HDR-IQA datasets are adopted for benchmarking: Narwaria2013, Valenzise2014, Zerman2017, and UPIQ.

A comprehensive robustness benchmark for Document Layout Analysis (DLA) models, including 450K document images from 3 datasets.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors tested their model on various signal reconstruction tasks: 1D sinusoidal...

The dataset contains images with various distortions, including blur, noise, and compression.

The dataset used in the paper for image quality assessment, consisting of images with various distortions.

The proposed method consists of four components: feature extractor using ViT, transposed attention block, scale swin transformer block, and a dual branch structure for...

The proposed model is designed to capture distortion-related patterns using a task transfer strategy simulating the from easy to hard human learning law.

The proposed model is designed to capture distortion-related patterns using a task transfer strategy simulating the from easy to hard human learning law.

With the popularity of smartphones and other camera devices in recent years, a vast amount of images have been produced and play an increasingly important role in people’s...

The Kodak PhotoCD dataset is a collection of 1000 images for image compression tasks.

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....