Blind Image Quality Assessment Using Joint Statistics of Gradient Magnitude and Laplacian Features

By Wufeng Xue, Xuanqin Mou, Lei Zhang, A. Bovik, Xiangchu Feng. IEEE Transactions on Image Processing, 2014

611 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/9d19b7c3d5f456061cc7a0f4d2af461fa8ebb3c8

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

1. Kede Ma
2. Lei Zhang
3. Dacheng Tao
4. Wangmeng Zuo
5. Zhou Wang
6. Jongyoo Kim
7. Sanghoon Lee
8. Luc Van Gool

In Media Technology

1. Kede Ma
2. Jongyoo Kim
3. Sanghoon Lee
4. Zhou Wang
5. Lei Zhang
6. Dacheng Tao
7. A. Bovik
8. Weixia Zhang

Citations in the corpus

• Blind Image Quality Assessment Using a Deep Bilinear Convolutional Neural Network (2019, methodology): “In this subsection, we conduct cross database validations to compare the generalizability of DB-CNN against BRISQUE [7], M3 [48], FRIQUEE [22], CORNIA [8], and HOSA [49].”
• Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network (2020, methodology): “the “blue sky” image when attack against GMLOG [9], the “mountain” image when attack against deep-IQA [1], and the “sunset” image when attack against DBCNN [12], while they indeed represent fairly good image quality.”
• dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs (2017, methodology): “From the model learning perspective, SVR [63], [64] is the most commonly used tool to learn f (x) for BIQA [6], [9], [10], [12], [45], [52].”
• UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content (2020, methodology): “baseline models include NIQE [53], ILNIQE [78], VIIDEO [55], BRISQUE [38], GM-LOG [57], HIGRADE [40], FRIQUEE [41], CORNIA [43], HOSA [61], KonCept512 [70], PaQ-2-PiQ [64], V-BLIINDS [39], and TLVQM [42].”
• MetaIQA: Deep Meta-Learning for No-Reference Image Quality Assessment (2020, methodology): “NR-IQA can be classified into distortion-specific methods [25, 24, 29, 47] and general-purpose methods [39, 32, 56, 51, 50, 12, 54, 49, 10].”
• A Feature-Enriched Completely Blind Image Quality Evaluator (2015, methodology): “Based on these observations (see also [23]), we use the empirically measured distribution parameters of image gradient components and gradient magnitudes as quality-aware NSS features for the opinion-unaware BIQA task.”
• 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]).”
• Blind Image Quality Assessment Based on High Order Statistics Aggregation (2016, background): “Xue et al. [20] propose GM-LOG which extracts competitive histogram-based features from the joint statistics of image gradients magnitude (GM) and Laplacian of Gaussian (LOG) responses.”
• Group MAD Competition? A New Methodology to Compare Objective Image Quality Models (2016, background): “The four distortion types are common in existing IQA databases [27, 23] and many IQA models are claimed to be able to properly handle these distortions [19, 20, 25, 17, 40, 18, 38, 37, 26, 42, 36, 7, 35].”