A Feature-Enriched Completely Blind Image Quality Evaluator

By Lin Zhang, Lei Zhang, A. Bovik. IEEE Transactions on Image Processing, 2015

1,229 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/cdda8e0c4429a3604dbccdf2679410d38bbd36bc

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

Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment (2016, result): “TABLE III: SROCC results of the cross-dataset evaluations with comparable results taken from [31].”
Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild (2020, methodology): “[26] extended NIQE [10] by exploiting a more powerful set of NSS for local quality prediction.”
Visual Quality Enhancement Of Images Under Adverse Weather Conditions (2018, methodology): “Here we use Blind Image Quality Assessment(BIQA) [34]measure to get an estimate about the visual quality of a stand alone image.”
SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution (2023, neutral): “NIQE [71], MANIQA [64], MUSIQ [64], and CLIPIQA [64] are no-reference image quality measures.”
Blind Image Quality Assessment Based on High Order Statistics Aggregation (2016, methodology): “Recently Zhang et al. [23] extract abundant perceptual patch level features from pristine images, and measured the distance between distorted image and pristine images via multivariate Gaussian (MVG) model.”
Exploring CLIP for Assessing the Look and Feel of Images (2022, methodology): “The core idea of these methods is to hand-craft degradation-aware features to characterize NSS and obtain the final quality score using regression models [29, 31] or multivariate Gaussian model [32, 45, 66].”
TOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment (2023, methodology): “Traditional approaches for NR-IQA rely on natural scene statistics (NSS) [6], [29], [30], [31], [32], [33].”
MUSIQ: Multi-scale Image Quality Transformer (2021, background): “In the past years, researchers proposed many IQA methods: early natural scene statistics based [13, 25, 27, 45], codebook-based [38, 40] and CNN-based [11, 33, 34, 41, 47].”
Blind Quality Assessment Based on Pseudo-Reference Image (2018, methodology): “• OU-BIQA models: NIQE [39] and IL-NIQE [40] use spatial domain NSS. QAC [41] performs quality-aware clustering and learns a codebook.”
Waterloo Exploration Database: New Challenges for Image Quality Assessment Models (2017, methodology): “(A, B) corresponds to the images for which the quality predictions by NIQE [34] and ILNIQE [14] are maximized/minimized.”
MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment (2022, background): “, poor lighting conditions, sensor limitations) [28, 34, 55].”
Group MAD Competition? A New Methodology to Compare Objective Image Quality Models (2016, methodology): “These include FR models 1) PSNR, 2) S- SIM [32], 3) MS-SSIM [34], 4) FSIM [43] and NR models 5) BIQI [19], 6) BLINDS II [25], 7) BRISQUE [17], 8) CORNIA [40], 9) DIIVINE [20], 10) IL-NIQE [42], 11) LPSI [36], 12) M3 [37], 13) NFERM [7], 14) NIQE [18], 15) QAC [38] and 16) TCLT [35] .”
End-to-End Blind Image Quality Assessment Using Deep Neural Networks (2018, methodology): “The competing algorithms are chosen to cover a diversity of design philosophies, including three classic ones: DIIVINE [3], BRISQUE [4] and CORNIA [38], and five state-of-the-art ones: ILNIQE [40], BLISS [22], HOSA [41], dipIQ [23] and”
UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content (2020, methodology): “These baseline models include NIQE [49], ILNIQE [74], VIIDEO [51], BRISQUE [36], GM-LOG [53], HIGRADE [38], FRIQUEE [39], CORNIA [41], HOSA [57], V-BLIINDS [37], and TLVQM [40].”
Perceptual quality prediction on authentically distorted images using a bag of features approach (2016, background): “The Laplacian of the luminance map of a pristine image is well-modeled as AGGD, but this property is disrupted by image distortions (L. Zhang, Zhang, & Bovik, 2015).”
No-Reference Quality Metric of Contrast-Distorted Images Based on Information Maximization (2017, neutral): “NR-IQA methods are made up of prevailing BRISQUE [12], NFERM [13] and IL-NIQE [14].”
Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data (2018, methodology): “In this comparison, apart from our BIQME method, we mainly consider the following 13 state-of-the-art IQA models, which encompass: 1) FR FSIM [8], LTG [9], VSI [10], PSIM [11], and C-PCQI; 2) RR RRED [15], FTQM [16], RIQMC [30], and QMC [34]; and 3) NR NIQE [19], IL-NIQE [20],”
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.”
Deep CNN-Based Blind Image Quality Predictor (2019, methodology): “methods (BLIINDS II [2], BRISQUE [11], CORNIA [15], ILNIQE [38], GMLOG [39], HOSA [16], and NRSL [40]).”