No-Reference Image Quality Assessment in the Spatial Domain

By Anish Mittal, Anush K. Moorthy, A. Bovik. 2012

5,860 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Effects of Degradations on Deep Neural Network Architectures (2018, background): “Though there are several no-reference image quality measures available in literature [1], visual quality of an input image is a subjective quantity and traditionally we rely on human perception to conclude about it.”
The Perception-Distortion Tradeoff (2017, methodology): “[26] which is specifically designed for SR quality assessment (see Supplementary for experiments with the NR metrics BRISQUE [29], NIQE [30] and BLIINDS-II [37]).”
An Experiment-Based Review of Low-Light Image Enhancement Methods (2020, methodology): “…are several general methods available for image quality evaluation, including the Blind/Referenceless Image Spatial QUality Evaluator (BRISQUE) [288], the Naturalness Image Quality Evaluator (NIQE) [289], the BLind Image Integrity Notator using DCT Statistics (BLIINDS-II) [290], the blind…”
The 2018 PIRM Challenge on Perceptual Image Super-Resolution (2018, background): “[22], NIQE [27], BRISQUE [26] and the PI defined by (1).”
Using labeled data to evaluate change detectors in a multivariate streaming environment (2009, neutral): “To this end, we propose a two-branch segmentation network, i.e. FastICENet, for accuracy and eﬃciency improvement.”
Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network (2020, methodology): “Distribution models used to capture the statistics from synthetically distorted image include generalized Gaussian distribution (GGD) [29, 30], asymmetric generalized Gaussian distribution (AGGD) [3, 29], Weibull distribution [3], third order”
Perceptual image quality assessment using a normalized Laplacian pyramid (2016, neutral): “Specifically, one could use a measure of mutual information (or another measure of statistical independence) of the normalized Laplacian representation of an image, to quantify its “naturalness” thus, the level of distortion), similar to the strategy followed in [32].”
Blind Image Quality Assessment Based on High Order Statistics Aggregation (2016, methodology): “Mittal et al. [18] utilize GGD to describe the statistics of local normalized images to constitute an efficient BIQA model.”
Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment (2016, methodology): “Method CSIQ full DIIVINE [13] 0.146 BLIINDS-II [14] 0.456 BRISQUE [15] 0.639 CORNIA [16] 0.656 Patchwise (proposed) 0.717 Weighted (proposed) 0.733 LIVE database is evaluated on subsets of CSIQ and TID2013.”
Exploring CLIP for Assessing the Look and Feel of Images (2022, methodology): “Conventional NR-IQA methods [29, 31, 32, 45, 66] mainly rely on natural scene statistics (NSS) [44], a model revealing statistic property of natural images.”
Domain Fingerprints for No-Reference Image Quality Assessment (2019, background): “Numerous efforts [2], [5]–[11] have been made to extract powerful features to represent images and image degradations.”
No-Reference Quality Metric of Contrast-Distorted Images Based on Information Maximization (2017, neutral): “A majority of this type of methods depend on statistical regulations (see [12]–[15]).”
Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data (2018, methodology): “First, inspired by [17], [18], and [25], each testing data set was randomly separated into two teams based on image scenes.”
Blind Image Quality Estimation via Distortion Aggravation (2018, methodology): “Ten state-of-the-art blind IQA measures act as competitors in this paper, including: (1) NSS based measures, i.e., DIIVINE [15], BLIINDS2 [16], BRISQUE [17], NIQE [28], and ILNIQE [19]; (2) learning based measures, i.e., CORNIA [29] and HOSA [30]; (3) human vision based and some other measures, i.e.”