Most apparent distortion: full-reference image quality assessment and the role of strategy

By Eric C. Larson, Damon M. Chandler. 2010

2,038 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

Learning a No-Reference Quality Metric for Single-Image Super-Resolution (2016, methodology): “The CORNIA method learns a codebook from an auxiliary dataset [45] containing various image distortions.”
Seven Challenges in Image Quality Assessment: Past, Present, and Future Research (2013, methodology): “The first two of these modifications resulted in an approximately 17x speedup over the original MAD implementation.”
Blind Quality Assessment Based on Pseudo-Reference Image (2018, methodology): “1) Databases: Five large IQA databases are used as testbeds, including LIVE [9], TID2013 [10], CSIQ [11], SIQAD [12] and CCT [13].”
Using labeled data to evaluate change detectors in a multivariate streaming environment (2009, neutral): “Since each module is only responsible for obtaining relatively few new feature maps, the calculation cost can be greatly reduced and the prediction speed is improved.”
From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality (2019, background): “Full-Reference models: Many full-reference (FR) perceptual picture quality predictors, which make comparisons against high-quality reference pictures, are available [9, 10], [27, 28, 29, 30, 31, 32, 33].”
Exploring CLIP for Assessing the Look and Feel of Images (2022, methodology): “However, these methods requires training with human-labeled benchmarks (Larson and Chandler 2010; Sheikh, Sabir, and Bovik 2006; Ponomarenko et al. 2015; Ghadiyaram and Bovik 2015; Hosu et al. 2020; Fang et al. 2020), limiting their generalizability and versatility.”
Perceptual visual quality metrics: A survey (2011, methodology): “For VSNR, VIF, IFC and SSIM implementation, we have used the publicly accessible Matlab package [49]; they are the original codes provided by the respective algorithm designers.”
KADID-10k: A Large-scale Artificially Distorted IQA Database (2019, neutral): “of Ratings Subjective study Database Year Content distorted images Distortion type distortion types rated images per image environment IVC [5] 2005 10 185 artificial 4 185 15 lab LIVE [6] 2006 29 779 artificial 5 779 23 lab CSIQ [7] 2009 30 866 artificial 6 866 5∼7 lab TID2013 [2] 2013 25 3,000 arti”
A Haar wavelet-based perceptual similarity index for image quality assessment (2016, methodology): “To verify the generality of the HaarPSI, the same optimization procedure was repeated once only considering the TID 2008 and TID 2013 databases and once restricted to the LIVE and the CSIQ image databases.”
Blind image quality evaluation using perception based features (2015, methodology): “Even on CSIQ and TID databases, PIQUE is very competitive to QAC and NIQE and performed consistently better for White Noise in terms of both SROCC and PCC. Fast Fading (FF) was not considered in the above reports for consistency and comparison with QAC & NIQE.”