Objective quality assessment of multiply distorted images

By Dinesh Jayaraman, Anish Mittal, Anush K. Moorthy, A. Bovik. Asilomar Conference on Signals, Systems and Computers, 2012

335 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/cc9e067a4e377e57170e4197d6d5ffb7aedbb187

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. Xiaokang Yang
2. Kede Ma
3. Guangtao Zhai
4. Lei Zhang
5. Dacheng Tao
6. Weisi Lin
7. Luc Van Gool
8. Ming-Hsuan Yang

Citations in the corpus

• Massive Online Crowdsourced Study of Subjective and Objective Picture Quality (2015, methodology): “…set of distortions it is trained for), we evaluated the performance of the multi-model FRIQUEE algorithm on combinations of different image databases - the LIVE IQA Database [12] and the LIVE Multiply Distorted IQA Database [15], as well as the new LIVE In the Wild Image Quality Challenge Database.”
• Deep CNN-Based Blind Image Quality Predictor (2019, methodology): “proposed algorithm: LIVE IQA database [5], CSIQ [29], TID2013 [30], LIVE multiply distorted (LIVE MD) database [31], LIVE in the wild challenge (LIVE challenge) database [32], and Waterloo exploration database (WED) [33].”
• RankIQA: Learning from Rankings for No-Reference Image Quality Assessment (2017, background): “(5)Results on CSIQ [15] and MLIVE [9] are in supplementary material.”
• MetaIQA: Deep Meta-Learning for No-Reference Image Quality Assessment (2020, background): “However, their application scope is rather limited, considering the fact that the distortion type is usually unknown in real applications [15, 9].”
• Blind Image Quality Assessment Based on High Order Statistics Aggregation (2016, methodology): “It should be also mentioned that both TID2013 and MLIVE contain various types of distortions including several multiple and localized distortions.”
• CURE-OR: Challenging Unreal and Real Environments for Object Recognition (2018, methodology): “We validate the subjective quality estimation performance over LIVE [32], MULTI [33], and TID13 [34] databases, which include 4, 432 images and 30 distortion types.”
• No-Reference Quality Metric of Contrast-Distorted Images Based on Information Maximization (2017, positive): “A cross-validation is further conducted using the TID2013 database for training and using popular LIVE [37], CSIQ [23], and LIVEMD [38] databases for testing.”
• Perceptual quality prediction on authentically distorted images using a bag of features approach (2016, methodology): “, 2013) and CSIQ (Larson & Chandler, 2010) both of which contain single, synthetic distortions and LIVE-Multiply Database (Jayaraman et al., 2012), which contains Gaussian blur followed by JPEG compression distortions (in Part I) and Gaussian blur followed by additive white noise distortions (in Par”
• Blind Image Quality Assessment Using a Deep Bilinear Convolutional Neural Network (2019, methodology): “LIVE MD [43] contains 450 images generated from 15 source images with corruption under two multiple distortion scenarios, i.”