Fully Deep Blind Image Quality Predictor

By Jongyoo Kim, Sanghoon Lee. IEEE Journal on Selected Topics in Signal Processing, 2017

454 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/cab82c068afd4f87d2b5ab1389c4b47d664346f1

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. Lei Zhang
2. Kede Ma
3. Wangmeng Zuo
4. Luc Van Gool
5. Kai Zhang
6. Ming-Hsuan Yang
7. Dacheng Tao
8. Chen Change Loy

In Media Technology

1. Kede Ma
2. Lei Zhang
3. Zhou Wang
4. Wangmeng Zuo
5. Jongyoo Kim
6. Sanghoon Lee
7. Kai Zhang
8. Radu Timofte

Citations in the corpus

• Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network (2020, methodology): “The comparison methods including hand-crafted based approaches [3, 29, 37], deep learning based synthetic IQA approaches [2, 15] and deep learning based authentic IQA approaches [22, 44, 46].”
• Blind Image Quality Assessment Using a Deep Bilinear Convolutional Neural Network (2019, methodology): “It is worth noting that the aforementioned three methods [11], [17], [26] only partially”
• From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality (2019, background): “This unique picture quality map predictor is the first deep model that is learned from true human-generated picture and patch labels, rather than from proxy labels delivered by an algorithm, as in [45].”
• Deep Learning of Human Visual Sensitivity in Image Quality Assessment Framework (2017, methodology): “marked: SESANIA [7], CNN [8], a ‘Patchwise’ method in [2], and BIECON [9].”
• Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment (2016, methodology): “BIECON [28] proposes an interesting approach for data augmentation and tackles CNN-based NR IQA in 2 steps: First, a local quality is estimated based on normalized image patches employing a CNN of 2 convolutional, 2 pooling and 5 fully-connected layers.”
• Deep CNN-Based Blind Image Quality Predictor (2019, methodology): “As proposed in [21], SSIM [35] and FSIM [36] were used to generate the proxy targets.”
• MetaIQA: Deep Meta-Learning for No-Reference Image Quality Assessment (2020, methodology): “The five handcrafted feature-based NR-IQA methods are BLIINDSII [39], BRISQUE [32], ILNIQE [56], CORNIA [54] and HOSA [49], while the six deep learning-based NRIQA methods are BIECON [18], MEON [30], WaDIQaMNR [2], DistNet-Q3 [3], DIQA [19] and NSSADNN [52].”
• End-to-End Blind Image Quality Assessment Using Deep Neural Networks (2018, methodology): “ture extraction or a preprocessing step for DNN-based BIQA models [15], [16], [21].”