Using Free Energy Principle For Blind Image Quality Assessment

By Ke Gu, Guangtao Zhai, Xiaokang Yang, Wenjun Zhang. IEEE transactions on multimedia, 2015

582 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/c7c27c520cca5d874460d46639f8e8d7cc39ecd5

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

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].”
Domain Fingerprints for No-Reference Image Quality Assessment (2019, methodology): “Despite building NR-IQA models based on the free-energy theory, [3], [18] restore the distorted image with a linear autoregressive model, which is not capable of producing a satisfactory result when the input suffers from high-level distortion and therefore may not be consistent with HVS. Lin and…”
Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data (2018, methodology): “First, inspired by [17], [18], and [25], each testing data set was randomly separated into two teams based on image scenes.”
The Analysis of Image Contrast: From Quality Assessment to Automatic Enhancement (2016, methodology): “spatial quality evaluator (BRISQUE) [24], and no-reference free energy-based robust metric (NFERM) [25].”
Blind Image Quality Estimation via Distortion Aggravation (2018, methodology): “Following the common practices of training based IQA model evaluation [15]–[18], we split the image database into two completely separate sets: a training set with 80% distorted images and a testing set with the rest 20% distorted images.”
Blind Quality Assessment Based on Pseudo-Reference Image (2018, methodology): “NFERM [35] is based on free energy principle.”
From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality (2019, background): “No-reference (NR) or blind picture quality prediction is largely unsolved, though popular models exist [14, 15, 16, 17, 18, 19, 20].”
No-Reference Quality Metric of Contrast-Distorted Images Based on Information Maximization (2017, unknown): “NR-IQA methods are made up of prevailing blind/referenceless image spatial quality evaluator (BRISQUE) [12], NR free energy based robust metric (NFERM) [13], and integrated local natural image quality evaluator (IL-NIQE) [14].”
Structure-Revealing Low-Light Image Enhancement Via Robust Retinex Model (2018, background): “From the figure, we notice that the proposed method achieves the lowest NFERM score, which means that our results are more similar to natural images and have less distortion.”
Low-Light Image Enhancement With Semi-Decoupled Decomposition (2020, methodology): “The evaluation metrics include Natural Image Quality Evaluator (NIQE) [38], AutoRegressive-based Image Sharpness Metric (ARISM) [39] and No-reference Free Energy based Robust Metric (NFERM) [40].”
An Experiment-Based Review of Low-Light Image Enhancement Methods (2020, background): “…the no-reference image quality metric for contrast distortion (NIQMC) [294], the Global Contrast Factor (GCF) [295], the average information content (AIC) [296], the effective measure of enhancement (EME) [297], PixDist [298], and the no-reference free-energy-based robust metric (NFERM) [299].”
No-Reference Image Sharpness Assessment in Autoregressive Parameter Space (2015, methodology): “They are: 1) Three FR IQA models, peak signal-to-noise ratio (PSNR) that computes the signal energy preservation, structural similarity index (SSIM) that compares luminance, contrast and structural similarities [1], and VIF [2]; 2) Six NR IQA models, NFEQM [22], DIIVINE [24], BLIINDS-II [25], BRISQU”
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].”