No-Reference Image Quality Assessment in the Spatial Domain
Abstract
We propose a natural scene statistic-based distortion-generic blind/no-reference (NR) image quality assessment (IQA) model that operates in the spatial domain. The new model, dubbed blind/referenceless image spatial quality evaluator (BRISQUE) does not compute distortion-specific features, such as ringing, blur, or blocking, but instead uses scene statistics of locally normalized luminance coefficients to quantify possible losses of "naturalness" in the image due to the presence of distortions, thereby leading to a holistic measure of quality. The underlying features used derive from the empirical distribution of locally normalized luminances and products of locally normalized luminances under a spatial natural scene statistic model. No transformation to another coordinate frame (DCT, wavelet, etc.) is required, distinguishing it from prior NR IQA approaches. Despite its simplicity, we are able to show that BRISQUE is statistically better than the full-reference peak signal-to-noise ratio and the structural similarity index, and is highly competitive with respect to all present-day distortion-generic NR IQA algorithms. BRISQUE has very low computational complexity, making it well suited for real time applications. BRISQUE features may be used for distortion-identification as well. To illustrate a new practical application of BRISQUE, we describe how a nonblind image denoising algorithm can be augmented with BRISQUE in order to perform blind image denoising. Results show that BRISQUE augmentation leads to performance improvements over state-of-the-art methods. A software release of BRISQUE is available online: http://live.ece.utexas.edu/research/quality/BRISQUE_release.zip for public use and evaluation.
AI snapshot
Written from the paper’s full text.
TL;DR
BRISQUE is a no-reference, distortion-generic image quality model that operates in the spatial domain by fitting natural scene statistics of locally normalized luminance coefficients and their pairwise products, then mapping features to quality with SVR. It is statistically better than PSNR and SSIM, competitive with NR methods, efficient, and useful for blind denoising.
Key findings
- On the LIVE IQA database, BRISQUE achieved median SROCC 0.9395 and LCC 0.9424 across 1000 train-test splits; it was statistically better than full-reference PSNR and SSIM, highly competitive with NR algorithms, and slightly inferior to FR MS-SSIM.
- BRISQUE features also supported distortion classification, with median accuracy 88.6% overall: WN 100.0%, Blur 96.7%, JPEG 88.9%, JP2K 82.9%, and FF 83.3%; FF and JP2K were most confused.
- Computational complexity was low: for a 512 × 768 image on a 1.8-GHz single-core PC with 2 GB RAM, BRISQUE took 1 s, versus DIIVINE 149 s, BLIINDS-II 70 s, and PSNR 0.05 s.
- BRISQUE-augmented BM3D blind denoising was statistically superior to reference BM3D at the 95% confidence level for all simulated noise variances except 0.0316; on TID2008, BRISQUE’s overall SROCC was 0.896, compared with PSNR 0.870 and SSIM 0.902.
Methods
- The model computes mean subtracted contrast normalized (MSCN) coefficients via local mean subtraction and divisive normalization, fits a GGD to MSCN coefficients, and fits AGGD models to pairwise products along horizontal, vertical, main-diagonal, and secondary-diagonal orientations. It extracts 36 features (18 per scale at two scales) and maps them to quality using an SVM regressor with an RBF kernel.
- Evaluation used the LIVE IQA database (29 reference images, 779 distorted images, five distortion categories), with random 80% training / 20% testing splits, no content overlap, 1000 repetitions, and median SROCC/LCC; statistical significance was assessed with one-sided t-tests.
- Database independence was tested by training on all of LIVE and applying BRISQUE to TID2008; blind denoising used 300 Berkeley images, 10 Gaussian noise levels (3000 noisy images), 1000 training and 2000 testing images, with BRISQUE features predicting the BM3D input noise parameter.
Limitations
- Stated: BRISQUE remains slightly inferior to FR MS-SSIM, indicating room for improvement; the two-stage version showed a slight dip attributed to imperfect distortion identification; TID2008 testing used only 24 natural images and only distortions BRISQUE was trained for (JPEG, JP2K, WN, blur; FF absent); performance decreases when the window size becomes fairly large.
- Evident from the text: BRISQUE requires a training/calibration procedure with subjective quality scores, and its evaluation and denoising application depend on known distortion or noise conditions used in training.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
0 of 25 cited sources checked · 0 supported · 0 flagged
- Findingown data§ A. Natural Scene Statistics in the Spatial Domain · p. 6
Different distortions occupy different parts of the AGGD parameter space.
“It can be visualized that different distortions occupy different parts of the space.”
Quote in the paperSubstantial claim - Findingown data§ A. Natural Scene Statistics in the Spatial Domain · p. 4
Pristine and distorted images occupy different regions in the GGD parameter space.
“As shown in Fig. 5(a), pristine and distorted images occupy different regions in this parameter space.”
Quote in the paperSubstantial claim - Findingown data§ No-Reference Image Quality Assessment in the Spatial Domain · p. 1
BRISQUE is highly competitive with respect to all present-day distortion-generic NR IQA algorithms.
“Despite its simplicity, we are able to show that BRISQUE is statistically better than the full-reference peak signal-tonoise ratio and the structural similarity index, and is highly competitive with respect to all present-day distortion-generic NR IQA algorithms.”
Quote in the paperSubstantial claim - Findingown data§ A. Natural Scene Statistics in the Spatial Domain · p. 6
Increasing the number of scales beyond 2 did not contribute to performance much.
“We observed that increasing the number of scales beyond 2 did not contribute to performance much.”
Quote in the paperSubstantial claim - Findingown data§ No-Reference Image Quality Assessment in the Spatial Domain · p. 1
BRISQUE augmentation leads to performance improvements over state-of-the-art methods in blind image denoising.
“Results show that BRISQUE augmentation leads to performance improvements over state-of-the-art methods.”
Quote in the paperSubstantial claim
- Findingown data§ No-Reference Image Quality Assessment in the Spatial Domain · p. 1
BRISQUE is statistically better than the full-reference peak signal-to-noise ratio and the structural similarity index.
“Despite its simplicity, we are able to show that BRISQUE is statistically better than the full-reference peak signal-tonoise ratio and the structural similarity index, and is highly competitive with respect to all present-day distortion-generic NR IQA algorithms.”
Quote in the paperSubstantial claim - Findingcitation§ A. Natural Scene Statistics in the Spatial Domain · p. 4
A generalized Gaussian distribution can be used to effectively capture a broader spectrum of distorted image statistics, which often exhibit changes in the tail behaviour of the empirical coefficient distributions.
“We have found that a generalized Gaussian distribution (GGD) can be used to effectively capture a broader spectrum of distorted image statistics, which often exhibit changes in the tail behaviour (i.e. kurtosis) of the empirical coefficient distributions [32]”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [32] [32] K. Sharifi and A. Leon-Garcia, 'Estimation of shape parameter for generalized Gaussian distributions in subband decompositions of video,' IEEE Trans. Circuits Syst. Video Technol. , vol. 5, no. 1, pp. 52-56, Feb. 1995. - source
Not checked in the free run.
- Rests on an assumption: MSCN coefficient distributions are symmetric.
- Findingown data§ C. Statistical Significance and Hypothesis Testing · p. 10
BRISQUE remains slightly inferior to the full-reference MS-SSIM.
“We note that BRISQUE remains slightly inferior to the FR MS-SSIM, indicating that there may still be some room for improvement in performance.”
Quote in the paperNot a substantial claim - Findingown data§ V. APPLICATION TO BLIND IMAGE DENOISING · p. 12
The performance of BM3D drastically improves if a systematically different parameter selected based on perceptual quality is fed as input.
“The performance of the algorithm drastically improves, if a (systematically) different parameter selected based on perceptual quality is fed as input to the algorithm.”
Quote in the paperSubstantial claim - Findingown data§ VI. CONCLUSION · p. 13
BRISQUE efficiency is superior to other distortion-generic approaches to NR IQA.
“Further, we also showed that BRISQUE is computationally efficient and that its efficiency is superior to other distortion-generic approaches to NR IQA, thus making BRISQUE an attractive option for practical applications like image denoising.”
Quote in the paperSubstantial claim - Findingreasoning§ V. APPLICATION TO BLIND IMAGE DENOISING · p. 11
BRISQUE features can transform a nonblind image denoising algorithm into a blind image denoising algorithm.
“In this section, we describe one such approach, where the BRISQUE features are used to transform a nonblind image denoising algorithm into a blind image denoising algorithm.”
- Also stated in: § VI. CONCLUSION · p. 13 · boosted
“We demonstrated this application by augmenting non-blind image denoising algorithms using the BRISQUE features to produce blind image denoising algorithms.”
Quote in the paperSubstantial claim- Rests on an assumption: Existing blind image denoising algorithms typically address parameter estimation in an ad-hoc fashion without regard to natural scene statistics.
- Also stated in: § VI. CONCLUSION · p. 13 · boosted
- Findingown data§ F. Database Independence · p. 11
BRISQUE performs well in terms of correlation with human perception of quality on the TID2008 database.
“It should be clear that BRISQUE performs well in terms of correlation with human perception of quality and that the performance does not depend on the database.”
Quote in the paperSubstantial claim - Findingown data§ VI. CONCLUSION · p. 13
The statistical features extracted by BRISQUE correlate with human perception.
“We detailed the algorithm and the statistical features extracted, and demonstrated how each of these features correlate with human perception.”
Quote in the paperSubstantial claim - Findingown data§ V. APPLICATION TO BLIND IMAGE DENOISING · p. 12
BRISQUE augmented BM3D produces much higher quality denoised images than the baseline BM3D.
“It is clear that BRISQUE augmented BM3D produces much higher quality images than the baseline BM3D.”
- Also stated in: § V. APPLICATION TO BLIND IMAGE DENOISING · p. 12 · boosted
“Given a new (unseen) test noisy image, the BRISQUE augmented BM3D approach predicts the accurate input to BM3D and denoises the image with (as we shall soon see) much higher visual quality than the baseline.”
Quote in the paperSubstantial claim - Also stated in: § V. APPLICATION TO BLIND IMAGE DENOISING · p. 12 · boosted
- Findingnone given§ I. INTRODUCTION · p. 1
BRISQUE demonstrates better ability to predict human judgments of quality than other popular FR and NR IQA models.
“that demonstrates better ability to predict human judgments of quality than other popular FR and NR IQA models; that is highly efficient; and that is useful for perceptually optimizing image processing algorithms such as denoising.”
Quote in the paperNot a substantial claim - Findingreasoning§ D. Classification Accuracy · p. 10
In the distortion classifier's confusion matrix, FF and JP2K are most confused with each other.
“We see from Fig. 10 that FF and JP2K are most confused with each other which is not surprising, since FF distortion is a combination of JP2K followed by packet-loss errors.”
Quote in the paperNot a substantial claim - Findingreasoning§ E. Two-Stage Performance · p. 10
The two-stage realization of BRISQUE has a slight dip in performance compared to the one-stage BRISQUE.
“In Table VII, we tabulate the median SROCC value across 1000 trials for the two-stage realization of BRISQUE. We also list the performances of BRISQUE for comparison purposes. The slight dip in the performance can be attributed to imperfect distortion identification in the first stage of the two-stage framework.”
Quote in the paperNot a substantial claim - Findingown data§ V. APPLICATION TO BLIND IMAGE DENOISING · p. 12
When the BM3D denoising algorithm is fed the true accurate noise variance, the performance of the denoiser is sub-par.
“However, our experiments suggest that when the algorithm is fed the true accurate noise-variance, the performance of the denoiser is sub-par.”
Quote in the paperSubstantial claim - Findingnone given§ V. APPLICATION TO BLIND IMAGE DENOISING · p. 11
A systematic perception-based parameter estimation approach results in better denoising performance.
“Here, we demonstrate a systematic perception-based parameter estimation approach that results in better denoising performance.”
Quote in the paperNot a substantial claim- Rests on an assumption: Existing blind image denoising algorithms typically address parameter estimation in an ad-hoc fashion without regard to natural scene statistics.
- Findingown data§ D. Classification Accuracy · p. 10
WN and Blur are generally not confused with other distortions in the distortion classifier.
“WN and Blur are generally not confused with other distortions.”
Quote in the paperNot a substantial claim - Findingown data§ I. INTRODUCTION · p. 3
BRISQUE performs well on independent databases.
“We show that BRISQUE performs well on independent databases, analyze its complexity and compare it with other NR IQA approaches.”
Quote in the paperSubstantial claim - Findingreasoning§ V. APPLICATION TO BLIND IMAGE DENOISING · p. 12
The automatic parameter prediction approach is capable of predicting the level of input noise to BM3D so that the output denoised image has the highest visual quality.
“Once trained, the automatic parameter prediction approach is capable of predicting the level of input noise to BM3D, so that the output denoised image has the highest visual quality.”
Quote in the paperSubstantial claim - Findingcitation§ D. Classification Accuracy · p. 10
BRISQUE features can be used for explicit distortion-identification.
“In order to demonstrate that BRISQUE features can also be used for explicit distortion-identification [48], we report the median classification accuracy of the classifier for each of the distortions in the LIVE database, as well as across all distortions in Table VI.”
- Also stated in: § VI. CONCLUSION · p. 13 · boosted
“We demonstrated that BRISQUE performance is independent of database content and BRISQUE features may be used for distortion-identification as well.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [48] [48] A. K. Moorthy and A. C. Bovik, 'A two-stage framework for blind image quality assessment,' in Proc. IEEE Int. Conf. Image Process. , Sep. 2010, pp. 2481-2484. -
Not checked in the free run.
- Also stated in: § VI. CONCLUSION · p. 13 · boosted
- Interpretationreasoning§ I. INTRODUCTION · p. 1
Deviations from the regularity of natural statistics, when quantified appropriately, enable the design of algorithms capable of assessing the perceptual quality of an image without the need for any reference image.
“Deviations from the regularity of natural statistics, when quantified appropriately, enable the design of algorithms capable of assessing the perceptual quality of an image without the need for any reference image.”
Quote in the paperNot a substantial claim - Premisecitation§ I. INTRODUCTION · p. 2
The assumption of a pristine nature of any reference is questionable, since all images are ostensibly distorted.
“Moreover, the assumption of a pristine nature of any reference is questionable, since all images are ostensibly distorted [14].”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [14] [14] A. C. Bovik, 'Perceptual image processing: Seeing the future,' Proc. IEEE , vol. 98, no. 11, pp. 1799-1803, Nov. 2010. - source
Not checked in the free run.
- Interpretationreasoning§ I. INTRODUCTION · p. 1
By quantifying natural image statistics and refraining from an explicit characterization of distortions, the approach to quality assessment is not limited by the type of distortions that afflict the image.
“By quantifying natural image statistics and refraining from an explicit characterization of distortions, our approach to quality assessment is not limited by the type of distortions that afflict the image.”
Quote in the paperSubstantial claim - Premisenone given§ A. Correlation With Human Opinions · p. 8
The BRISQUE approach requires a training procedure to calibrate the regressor module.
“Since the BRISQUE approach requires a training procedure to calibrate the regressor module, we divide the LIVE database into two randomly chosen subsets - 80% training and 20% testing - such that no overlap between train and test content occurs.”
Quote in the paperSubstantial claim - Premisecitation§ A. Natural Scene Statistics in the Spatial Domain · p. 5
Under the Gaussian coefficient model, and assuming the MSCN coefficients are zero mean and unit variance, the products of neighboring MSCN coefficients obey a specified asymmetric distribution in the absence of distortion.
“Under the Gaussian coefficient model, and assuming the MSCN coeffficients are zero mean and unit variance, these products obey the following distribution in the absence of distortion [34]:”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [34] [34] A. H. Nuttall, 'Accurate efficient evaluation of cumulative or exceedance probability distributions directly from characteristic functions,' Naval Underwater Systems Center, New London, CT, Tech. Rep. ADA133703, 1983. - source
Not checked in the free run.
- The authors state this as an assumption: The MSCN coefficients are zero mean and unit variance.
- Premisecitation§ A. Natural Scene Statistics in the Spatial Domain · p. 6
Incorporating multiscale information when assessing quality produces QA algorithms that perform better in terms of correlation with human perception.
“Further, as research in quality assessment has demonstrated, incorporating multiscale information when assessing quality produces QA algorithms that perform better in terms of correlation with human perception [13], [29].”
Quote in the paperSubstantial claim0 of 2 sources checked- cites [13] [13] M. Saad, A. C. Bovik, and C. Charrier, 'Blind image quality assessment: A natural scene statistics approach in the DCT domain,' IEEE Trans. Image Process. , vol. 21, no. 8, pp. 3339-3352, Aug. 2012. - source
Not checked in the free run.
- cites [29] [29] Z. Wang, E. P. Simoncelli, and A. C. Bovik, 'Multiscale structural similarity for image quality assessment,' in Proc. Asilomar Conf. Signals, Syst. Comput. , vol. 2. 2003, pp. 1398-1402. -
Not checked in the free run.
- Premisecitation§ I. INTRODUCTION · p. 1
Most current NR IQA approaches are distortion-specific, i.e., they can perform blind IQA only if the distortion that afflicts the image is known beforehand.
“Such approaches to NR IQA are significant since most current approaches are distortion-specific [5]-[11], i.e., they are capable of performing blind IQA only if the distortion that afflicts the image is known beforehand, e.g., blur or noise or compression and so on (see below).”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [5]-[11]
Not checked in the free run.
- Premisenone given§ I. INTRODUCTION · p. 2
BRISQUE introduces a new model of the statistics of pair-wise products of neighboring locally normalized luminance values.
“BRISQUE introduces a new model of the statistics of pair-wise products of neighboring (locally normalized) luminance values.”
Quote in the paperSubstantial claim - Interpretationnone given§ I. INTRODUCTION · p. 1
BRISQUE is useful for perceptually optimizing image processing algorithms such as denoising.
“that is useful for perceptually optimizing image processing algorithms such as denoising.”
Quote in the paperNot a substantial claim - Interpretationown data§ F. Database Independence · p. 11
BRISQUE performance is not bound by the database on which it is tested.
“Having evaluated BRISQUE on the LIVE IQA database, we now demonstrate that the performance of BRISQUE is not bound by the database on which it is tested.”
- Also stated in: § F. Database Independence · p. 11 · boosted
“It should be clear that BRISQUE performs well in terms of correlation with human perception of quality and that the performance does not depend on the database.”
- Also stated in: § VI. CONCLUSION · p. 13 · boosted
“We demonstrated that BRISQUE performance is independent of database content and BRISQUE features may be used for distortion-identification as well.”
Quote in the paperSubstantial claim - Also stated in: § F. Database Independence · p. 11 · boosted
- Interpretationown data§ G. Computational Complexity · p. 11
The spatial-domain BRISQUE is an ideal candidate for real-time blind assessment of visual quality.
“This suggests that the spatial-domain BRISQUE an ideal candidate for real-time blind assessment of visual quality.”
Quote in the paperSubstantial claim - Interpretationown data§ C. Statistical Significance and Hypothesis Testing · p. 10
To the extent distortions can be trained on, one can replace full-reference algorithms such as SSIM with BRISQUE without any loss of performance.
“This result suggests that to the extent distortions can be trained on, one can replace full reference algorithms such as SSIM with the proposed BRISQUE without any loss of performance.”
Quote in the paperSubstantial claim
- May combine two claims. 23
- Classified as probably not a substantial claim. 18
- The quote only partly states this claim. 1
May combine two claims.
Findingnone given§ A. Natural Scene Statistics in the Spatial Domain · p. 5MSCN coefficients are more homogenous for pristine images, but the signs of adjacent coefficients exhibit a regular structure that gets disturbed in the presence of distortion.
“While MSCN coefficients are definitely more homogenous for pristine images, the signs of adjacent coefficients also exhibit a regular structure, which gets disturbed in the presence of distortion.”
Quote in the paperSubstantial claimMay combine two claims.
Findingcitation§ A. Natural Scene Statistics in the Spatial Domain · p. 4JPEG2000 and fast fading have a high degree of overlap in GGD parameter space because fast fading images in the LIVE database are multidistorted, first compressed into a bitstream using a JPEG2000 codec, then passed through a Rayleigh fast fading channel to simulate packet loss.
“JPEG2000 and fast fading have a high degree of overlap as fast fading images in LIVE database are actually multidistorted, first compressed into a bitstream using a JPEG2000 codec, then passed through a Rayleigh fast fading channel to simulate packet loss [27].”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [27] [27] H. R. Sheikh, M. F. Sabir, and A. C. Bovik, 'A statistical evaluation of recent full reference image quality assessment algorithms,' IEEE Trans. Image Process. , vol. 15, no. 11, pp. 3440-3451, Nov. 2006. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
May combine two claims.
Findingown data§ I. INTRODUCTION · p. 1The normalized luminance coefficients of a natural image closely follow a Gaussian-like distribution, whereas the empirical distribution of an artificial image does not.
“The normalized luminance coefficients (explained later) of the natural image closely follow Gaussian-like distribution, as shown in Fig. 1(c) while the same doesnot hold for the empirical distribution of the artificial image shown in Fig. 1(d).”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [4] [4] N. Ponomarenko, V. Lukin, A. Zelensky, K. Egiazarian, M. Carli, and F. Battisti, 'TID2008-a database for evaluation of full-reference visual quality assessment metrics,' Adv. Modern Radioelectron. , vol. 10, no. 10, pp. 30-45, 2009. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Findingnone given§ No-Reference Image Quality Assessment in the Spatial Domain · p. 1BRISQUE has very low computational complexity, making it well suited for real time applications.
“BRISQUE has very low computational complexity, making it well suited for real time applications.”
Quote in the paperNot a substantial claimThe quote only partly states this claim.
Findingown data§ A. Natural Scene Statistics in the Spatial Domain · p. 7The extracted features correlate with human DMOS for each distortion in the LIVE IQA database.
“In Fig. 8, we plot the Spearman's rank ordered correlation coefficient (SROCC) between each of these features and human DMOS from the LIVE IQA database, for each of the distortions in the database JPEG and JPEG2000 compression, additive white Gaussian noise, Gaussian blur and a Rayleigh fast fading channel distortion, to ascertain how well the features correlate with human judgments of quality.”
Quote in the paperSubstantial claimMay combine two claims.
Findingown data§ A. Natural Scene Statistics in the Spatial Domain · p. 6The single-parameter density function for products of adjacent normalized coefficients is a good model of the empirical histograms of products of adjacent normalized coefficients, but it does not provide a good fit to the empirical histograms of coefficient products from distorted images and is not finite at the origin.
“While we have found that this density function is a good model of the empirical histograms of products of adjacent normalized coefficients, it has only a single parameter, and as such, does not provide a good fit to the empirical histograms of coefficient products (Fig. 2) from distorted images. Further, it is not finite at the origin.”
Quote in the paperSubstantial claimMay combine two claims.
Findingown data§ A. Natural Scene Statistics in the Spatial Domain · p. 4White noise is very clearly separated from the pristine image set in GGD parameter space, making it one of the easiest distortions to gauge quality of.
“White noise is very clearly separated from the pristine image set making it one of the easiest to gauge the quality of”
Quote in the paperNot a substantial claimMay combine two claims.
Findingown data§ C. Statistical Significance and Hypothesis Testing · p. 10On the LIVE IQA database, BRISQUE is highly competitive with all no-reference algorithms tested and statistically better than the full-reference algorithms PSNR and SSIM.
“From Table V we conclude that BRISQUE is highly competitive with all no reference algorithms tested and statistically better than the full reference algorithms PSNR and SSIM.”
- Also stated in: § VI. CONCLUSION · p. 13 · boosted
“We then undertook a thorough evaluation of the BRISQUE index in terms of correlation with human perception and demonstrated that BRISQUE is statistically better than FR PSNR and SSIM as well as highly competitive to all NR algorithms compared with.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [47] [47] D. Sheskin, Handbook of Parametric and Nonparametric Statistical Procedures . London, U.K.: Chapman & Hall, 2004. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Also stated in: § VI. CONCLUSION · p. 13 · boosted
May combine two claims.
Findingown data§ V. APPLICATION TO BLIND IMAGE DENOISING · p. 12Our approach produces better visual quality and better objective quality, as gauged by MS-SSIM, than using the true noise variance.
“Notice that our approach produces better visual quality, and better objective quality, as gauged by the multi-scale structural similarity index (MS-SSIM) [29].”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [29] [29] Z. Wang, E. P. Simoncelli, and A. C. Bovik, 'Multiscale structural similarity for image quality assessment,' in Proc. Asilomar Conf. Signals, Syst. Comput. , vol. 2. 2003, pp. 1398-1402. -
Not checked in the free run.
May combine two claims.
Findingown data§ V. APPLICATION TO BLIND IMAGE DENOISING · p. 12For all noise variances simulated in the present data, our approach is statistically superior to the reference BM3D implementation in terms of perceived visual quality at the 95% confidence level, except when the noise variance is 0.0316, where the two approaches become statistically indistinguishable.
“Our analysis indicates that for all noise variances simulated in the present data, our approach is statistically superior to the reference BM3D implementation in terms of perceived visual quality at the 95% confidence level, excepting when the noise variance is a tiny 0.0316 - where the two approaches become statistically indistinguishable.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [55] [55] L. V. Hedges and I. Olkin, Statistical Methods for Meta-Analysis . New York: Academic, 1985. <!-- image --> Anish Mittal received the B.Tech. degree in electrical engineering from the Indian Institute of Technology Roorkee, Roorkee, India, and the M.S. degree in computer engineering from The University of Texas at Austin, Austin, in 2009 and 2011, respectively. He joined the Laboratory for Image and Video Engineering, The University of Texas at Austin, in 2009, where he has been an Assistant Director since January 2012. His research interests include image and video processing, machine le
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingnone given§ D. Classification Accuracy · p. 10JP2K and JPEG are also confused sometimes in the distortion classifier.
“JP2K and JPEG are also confused sometimes.”
Quote in the paperNot a substantial claimMay combine two claims.
Findingown data§ G. Computational Complexity · p. 11BRISQUE is computationally efficient and has low complexity.
“Having demonstrated that BRISQUE performs well in terms of correlation with human perception, we also now show that BRISQUE has low complexity.”
- Also stated in: § VI. CONCLUSION · p. 13 · boosted
“Further, we also showed that BRISQUE is computationally efficient and that its efficiency is superior to other distortion-generic approaches to NR IQA, thus making BRISQUE an attractive option for practical applications like image denoising.”
Quote in the paperSubstantial claim- Also stated in: § VI. CONCLUSION · p. 13 · boosted
May combine two claims.
Findingown data§ G. Computational Complexity · p. 11BRISQUE is quite efficient, outperforming the DIIVINE index and the BLIINDS-II index by a large amount.
“As Table X demonstrates, BRISQUE is quite efficient, outperforming the DIIVINE index and the BLIINDS-II index by a large amount.”
Quote in the paperSubstantial claimMay combine two claims.
Findingown data§ B. Variation With Window Size · p. 9BRISQUE performance remains relatively stable with respect to variation in the window size used to compute the local mean and variances, but decreases when the window size becomes fairly large as the computations become non-local.
“As observed from the Table IV, the performance of BRISQUE remains relatively stable with respect to variation in the window size used to compute the local mean and variances. However, the performance starts to decrease when it becomes fairly large as the computations become non-local.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
Premisecitation§ A. Correlation With Human Opinions · p. 7Each distorted image in the LIVE IQA database has an associated difference mean opinion score (DMOS) representing the subjective quality of the image.
“Each of the distorted images has an associated difference mean opinion score (DMOS) which represents the subjective quality of the image.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [27] [27] H. R. Sheikh, M. F. Sabir, and A. C. Bovik, 'A statistical evaluation of recent full reference image quality assessment algorithms,' IEEE Trans. Image Process. , vol. 15, no. 11, pp. 3440-3451, Nov. 2006. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone given§ No-Reference Image Quality Assessment in the Spatial Domain · p. 1BRISQUE features may be used for distortion-identification.
“BRISQUE features may be used for distortion-identification as well.”
Quote in the paperNot a substantial claimMay combine two claims.
Premisenone given§ I. INTRODUCTION · p. 2BRISQUE utilizes an NSS model framework of locally normalized luminance coefficients and quantifies naturalness using the parameters of the model.
“The product of our research is the Blind/Referenceless Image Spatial QUality Evaluator (BRISQUE) which utilizes an NSS model framework of locally normalized luminance coefficients and quantifies 'naturalness' using the parameters of the model.”
Quote in the paperSubstantial claimClassified as probably not a substantial claim.
Premisereasoning§ I. INTRODUCTION · p. 2The performance of any IQA model is best gauged by its correlation with human subjective judgements of quality.
“The performance of any IQA model is best gauged by its correlation with human subjective judgements of quality, since the human is the ultimate receiver of the visual signal.”
Quote in the paperSubstantial claimClassified as probably not a substantial claim. May combine two claims.
Study design and conductreasoning§ A. Correlation With Human Opinions · p. 8The random train-test procedure was repeated 1000 times and the median performance across these iterations was reported to eliminate performance bias.
“Further, we repeat this random train-test procedure 1000 times and report the median of the performance across these 1000 iterations, in order to eliminate performance bias.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ I. INTRODUCTION · p. 2The regularity of natural scene statistics has been well established in the visual science literature, with regularity demonstrated in the spatial domain and in the wavelet domain.
“The regularity of natural scene statistics (NSS) has been well established in the visual science literature, where regularity has been demonstrated in the spatial domain [15], and in the wavelet domain [16].”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites [15] [15] D. L. Ruderman, 'The statistics of natural images,' Netw. Comput. Neural Syst. , vol. 5, no. 4, pp. 517-548, 1994. -
Not checked in the free run.
- cites [16] [16] A. Srivastava, A. B. Lee, E. P. Simoncelli, and S. C. Zhu, 'On advances in statistical modeling of natural images,' J. Math. Imag. Vis. , vol. 18, no. 1, pp. 17-33, 2003. -
Not checked in the free run.
May combine two claims.
Interpretationreasoning§ I. INTRODUCTION · p. 2Characterizing locally normalized luminance coefficients in this way is sufficient not only to quantify naturalness, but also to quantify quality in the presence of distortion.
“Our claim is that characterizing locally normalized luminance coefficients in this way is sufficient not only to quantify naturalness, but also to quantify quality in the presence of distortion.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ A. Correlation With Human Opinions · p. 8PSNR is a poor measure of perceptual quality.
“Although PSNR is a poor measure of perceptual quality, it is often used to benchmark for QA algorithms [41], [42].”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites [41] [41] Z. Wang and A. C. Bovik, 'Mean squared error: Love it or leave it? A new look at signal fidelity measures,' IEEE Signal Process. Mag. , vol. 26, no. 1, pp. 98-117, Jan. 2009. - source
Not checked in the free run.
- cites [42] [42] B. Girod, 'What's wrong with mean squared error?' in Visual Factors of Electronic Image Communications , A. B. Watson Ed. Cambridge, MA: MIT Press, 1993, pp. 207-220. -
Not checked in the free run.
May combine two claims.
Study design and conductreasoning§ A. Correlation With Human Opinions · p. 8The LIVE database was divided into two randomly chosen subsets, 80% training and 20% testing, with no overlap between train and test content.
“we divide the LIVE database into two randomly chosen subsets - 80% training and 20% testing - such that no overlap between train and test content occurs.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ I. INTRODUCTION · p. 2The power spectrum of natural images is a function of frequency and takes the form 1/f^γ, where γ varies over a small range across natural images.
“For example, it is well known that the power spectrum of natural images is a function of frequency and takes the form 1 / f γ , where γ is an exponent that varies over a small range across natural images.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites [15] [15] D. L. Ruderman, 'The statistics of natural images,' Netw. Comput. Neural Syst. , vol. 5, no. 4, pp. 517-548, 1994. -
Not checked in the free run.
- cites [16] [16] A. Srivastava, A. B. Lee, E. P. Simoncelli, and S. C. Zhu, 'On advances in statistical modeling of natural images,' J. Math. Imag. Vis. , vol. 18, no. 1, pp. 17-33, 2003. -
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationnone given§ No-Reference Image Quality Assessment in the Spatial Domain · p. 1A nonblind image denoising algorithm can be augmented with BRISQUE in order to perform blind image denoising.
“To illustrate a new practical application of BRISQUE, we describe how a nonblind image denoising algorithm can be augmented with BRISQUE in order to perform blind image denoising.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ A. Correlation With Human Opinions · p. 7The LIVE IQA database consists of 29 reference images with 779 distorted images spanning five distortion categories: JPEG2000, JPEG compression, additive white Gaussian noise, Gaussian blur, and a Rayleigh fast-fading channel simulation.
“We used the LIVE IQA database [27] to test the performance of BRISQUE, which consists of 29 reference images with 779 distorted images spanning five different distortion categories - JPEG2000 (JP2K) and JPEG compression, additive white Gaussian noise (WN), Gaussian blur (Blur), and a Rayleigh fast-fading channel simulation (FF).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites [27] [27] H. R. Sheikh, M. F. Sabir, and A. C. Bovik, 'A statistical evaluation of recent full reference image quality assessment algorithms,' IEEE Trans. Image Process. , vol. 15, no. 11, pp. 3440-3451, Nov. 2006. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationreasoning§ E. Two-Stage Performance · p. 10The slight dip in the two-stage BRISQUE performance can be attributed to imperfect distortion identification in the first stage of the two-stage framework.
“The slight dip in the performance can be attributed to imperfect distortion identification in the first stage of the two-stage framework.”
Quote in the paperNot a substantial claimMay combine two claims.
Premisereasoning§ I. INTRODUCTION · p. 1BRISQUE is purely spatial and transform-free, not requiring a mapping to another coordinate domain such as wavelet or DCT.
“Our contribution here is a new NR IQA model that is purely spatial; that relies on a spatial NSS model which does not require a mapping to a different co-ordinate domain (wavelet, DCT, etc.) and so is 'transform-free';”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ V. APPLICATION TO BLIND IMAGE DENOISING · p. 11Blind image denoising remains relatively underexplored.
“Although image denoising is a well studied problem in image processing [50]-[54], blind image denoising remains relatively underexplored [49], [54].”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites [49] [49] X. Zhu and P. Milanfar, 'Automatic parameter selection for denoising algorithms using a no-reference measure of image content,' IEEE Trans. Image Process. , vol. 19, no. 12, pp. 3116-3132, Dec. 2010. -
Not checked in the free run.
- cites [54] [54] K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, 'Image denoising by sparse 3-D transform-domain collaborative filtering,' IEEE Trans. Image Process. , vol. 16, no. 8, pp. 2080-2095, Aug. 2007. -
Not checked in the free run.
Classified as probably not a substantial claim. May combine two claims.
Premisecitation§ V. APPLICATION TO BLIND IMAGE DENOISING · p. 12The denoising algorithm used is BM3D, which requires as input the noise variance in the image.
“The denoising algorithm that we use is the one proposed in [54], which requires as input the noise variance in the image.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [54] [54] K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, 'Image denoising by sparse 3-D transform-domain collaborative filtering,' IEEE Trans. Image Process. , vol. 16, no. 8, pp. 2080-2095, Aug. 2007. -
Not checked in the free run.
May combine two claims.
Study design and conductown data§ V. APPLICATION TO BLIND IMAGE DENOISING · p. 12In the denoising experiment, 1000 images were used for training and 2000 for testing, ensuring no content overlap between the two sets.
“1000 images were then used for training and 2000 for testing thereby ensuring no content overlap between the two sets.”
Quote in the paperSubstantial claimClassified as probably not a substantial claim.
Premisecitation§ F. Database Independence · p. 11The TID database consists of 25 reference images and 1700 distorted images over 17 distortion categories.
“The TID database consists of 25 reference images and 1700 distorted images over 17 distortion categories [4].”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [4] [4] N. Ponomarenko, V. Lukin, A. Zelensky, K. Egiazarian, M. Carli, and F. Battisti, 'TID2008-a database for evaluation of full-reference visual quality assessment metrics,' Adv. Modern Radioelectron. , vol. 10, no. 10, pp. 30-45, 2009. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
Classified as probably not a substantial claim.
Study design and conductreasoning§ G. Computational Complexity · p. 11Unoptimized MATLAB code was used for all algorithms in the complexity comparison to ensure a fair comparison.
“We use unoptimized MATLAB code for all of these algorithms in order to ensure a fair comparison.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Interpretationnone given§ V. APPLICATION TO BLIND IMAGE DENOISING · p. 12BRISQUE augmentation is not limited to the BM3D algorithm; any non-blind algorithm could be improved by using BRISQUE natural scene features to produce a blind image denoiser.
“Notice that BRISQUE augmentation is not limited to the BM3D algorithm; and any non-blind algorithm could be improved by using BRISQUE natural scene features to produce a blind image denoiser.”
Quote in the paperNot a substantial claim- Rests on an assumption: Existing blind image denoising algorithms typically address parameter estimation in an ad-hoc fashion without regard to natural scene statistics.
Classified as probably not a substantial claim.
Interpretationreasoning§ V. APPLICATION TO BLIND IMAGE DENOISING · p. 11BRISQUE is an attractive option for practical applications like image denoising.
“The computational efficiency and excellent quality prediction performance makes BRISQUE an attractive option for practical applications.”
- Also stated in: § VI. CONCLUSION · p. 13 · boosted
“Further, we also showed that BRISQUE is computationally efficient and that its efficiency is superior to other distortion-generic approaches to NR IQA, thus making BRISQUE an attractive option for practical applications like image denoising.”
Quote in the paperSubstantial claim- Also stated in: § VI. CONCLUSION · p. 13 · boosted
May combine two claims.
Premisecitation§ V. APPLICATION TO BLIND IMAGE DENOISING · p. 11The work in [49] is computationally intensive and its measure of content in the image may not be the ideal measure to predict noise variance.
“The work closest in concept to this approach is the one proposed in [49] where image content measures were used to predict the noise variance in the image, which was then used for image denoising; however the approach is computationally intensive and the measure of content in the image may not be the ideal measure to predict noise variance.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites [49] [49] X. Zhu and P. Milanfar, 'Automatic parameter selection for denoising algorithms using a no-reference measure of image content,' IEEE Trans. Image Process. , vol. 19, no. 12, pp. 3116-3132, Dec. 2010. -
Not checked in the free run.
The authors state this as an assumption.
The MSCN coefficients are zero mean and unit variance.
“assuming the MSCN coeffficients are zero mean and unit variance”
The paper relies on this without support.
Distortions affect image structure across scales.
“Images are naturally multiscale, and distortions affect image structure across scales.”
The paper relies on this without support.
MSCN coefficient distributions are symmetric.
“We choose the zero mean distribution, since (generally) MSCN coefficient distributions are symmetric.”
The paper relies on this without support.
Existing blind image denoising algorithms typically address parameter estimation in an ad-hoc fashion without regard to natural scene statistics.
“The proposed algorithms typically address parameter estimation in an ad-hoc fashion without regard to natural scene statistics.”
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
BRISQUE and MS-SSIM are each marked statistically superior to the other
MajorTable V assigns a value of 1 to both MS-SSIM versus BRISQUE and BRISQUE versus MS-SSIM. Under the table's stated definition, both algorithms cannot be statistically superior to each other. The latter entry also conflicts with the paper's conclusion that BRISQUE is slightly inferior to MS-SSIM.
“| MSSSIM | 1 | 1 | 0 | 1 | 1 | 1 | 1 | 1 |”
“| BRISQUE | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 0 |”
Parameter-estimation count omits the second scale
MinorThe features require one GGD fit and four orientation-specific AGGD fits at each scale. That is five fits per scale, or ten for an image processed at the stated two scales, rather than five for the entire image.
“parameter estimation needs to be performed only 5 times for an entire image”
“Hence, we extract all features listed in Table I at two scales -the original image scale, and at a reduced resolution (low pass filtered and downsampled by a factor of 2).”
PSNR and BLIINDS-II are each marked statistically superior to the other
MinorTable V assigns 1 to PSNR versus BLIINDS-II and also to BLIINDS-II versus PSNR. Both cannot be statistically superior to each other under the table's stated definition.
“| PSNR | 0 | - 1 | - 1 | - 1 | - 1 | 1 | - 1 | - 1 |”
“| BLIINDS-II | 1 | - 1 | - 1 | 1 | 1 | 0 | - 1 | - 1 |”
Cites
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892 · see citing works
Self-citationLIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918 · see citing works
A Tutorial on Support Vector Machines for Pattern Recognition
Burges, C. J. C. (1998) · Data Mining and Knowledge Discovery · doi:10.1023/a:1009715923555 · Cited by 16,437 · see citing works
Wasserman, S. S., Hedges, L. V., & Olkin, I. (1988) · Journal of Educational Statistics · doi:10.2307/1164953 · Cited by 10,347 · see citing works
Libsvm : A library for support vector machines
Ferrari, V. (2008) · Medical Entomology and Zoology · Cited by 10,124 · see citing works
Image denoising by sparse 3-D transform-domain collaborative filtering
Dabov, K., Foi, A., Katkovnik, V., & Egiazarian, K. (2007) · IEEE Transactions on Image Processing · doi:10.1109/tip.2007.901238 · Cited by 9,283 · see citing works
Martin, D., Fowlkes, C., Tal, D., & Malik, J. (2002) · Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 · doi:10.1109/iccv.2001.937655 · Cited by 8,216 · see citing works
A Non-Local Algorithm for Image Denoising
Buades, A., Coll, B., & Morel, J.-M. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.38 · Cited by 7,616 · see citing works
Multiscale structural similarity for image quality assessment
Wang, Z., Simoncelli, E. P., & Bovik, A. C. (2004) · The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003 · doi:10.1109/acssc.2003.1292216 · Cited by 6,253 · see citing works
Self-citationImage Denoising Via Sparse and Redundant Representations Over Learned Dictionaries
Elad, M., & Aharon, M. (2006) · IEEE Transactions on Image Processing · doi:10.1109/tip.2006.881969 · Cited by 5,321 · see citing works
Statistical Methods for Meta-Analysis.
Freeman, P. R., Hedges, L. V., & Olkin, I. (1986) · Biometrics · doi:10.2307/2531069 · Cited by 4,832 · see citing works
Handbook of Parametric and Nonparametric Statistical Procedures
(2004) · Technometrics · doi:10.1198/tech.2004.s209 · Cited by 4,664 · see citing works
Image information and visual quality
Sheikh, H. R., & Bovik, A. C. (2006) · IEEE Transactions on Image Processing · doi:10.1109/tip.2005.859378 · Cited by 4,104 · see citing works
Self-citationA TUTORIAL ON SUPPORT VECTOR MACHINES FOR PATTERN RECOGNITION, DATA MINING AND KNOWLEDGE DISCOVERY
Burger, C. J. C. (1998) · Cited by 3,261 · see citing works
Mean squared error: Love it or leave it? A new look at Signal Fidelity Measures
Wang, Z., & Bovik, A. C. (2009) · IEEE Signal Processing Magazine · doi:10.1109/msp.2008.930649 · Cited by 3,175 · see citing works
Self-citationA Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms
Sheikh, H. R., Sabir, M. F., & Bovik, A. C. (2006) · IEEE Transactions on Image Processing · doi:10.1109/tip.2006.881959 · Cited by 3,018 · see citing works
Self-citation(1999) · doi:10.1162/089976600300015565 · Cited by 2,799 · see citing works
Image denoising using scale mixtures of gaussians in the wavelet domain
Portilla, J., Strela, V., Wainwright, M. J., & Simoncelli, E. P. (2003) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.818640 · Cited by 2,256 · see citing works
Blind Image Quality Assessment: From Natural Scene Statistics to Perceptual Quality
Moorthy, A. K., & Bovik, A. C. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2147325 · Cited by 1,763 · see citing works
Self-citationBlind Image Quality Assessment: A Natural Scene Statistics Approach in the DCT Domain
Saad, M. A., Bovik, A. C., & Charrier, C. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2191563 · Cited by 1,750 · see citing works
Self-citationHandbook of Image and Video Processing
Bovik, A. C. (2005) · Elsevier eBooks · doi:10.1016/b978-0-12-119792-6.x5062-1 · Cited by 1,585 · see citing works
Self-citationAn information fidelity criterion for image quality assessment using natural scene statistics
Sheikh, H. R., Bovik, A. C., & de Veciana, G. (2005) · IEEE Transactions on Image Processing · doi:10.1109/tip.2005.859389 · Cited by 1,399 · see citing works
Self-citationA Two-Step Framework for Constructing Blind Image Quality Indices
Moorthy, A. K., & Bovik, A. C. (2010) · IEEE Signal Processing Letters · doi:10.1109/lsp.2010.2043888 · Cited by 1,196 · see citing works
Self-citationTID2008 – A database for evaluation of full-reference visual quality assessment metrics
Ponomarenko, N. N., Лукин, В. В., & Zelensky, A. A. (2004) · Iris (Roma Tre University) · Cited by 1,000 · see citing works
The statistics of natural images
Ruderman, D. (1994) · Network Computation in Neural Systems · doi:10.1088/0954-898x_5_4_006 · Cited by 945 · see citing works
Linearity and Normalization in Simple Cells of the Macaque Primary Visual Cortex
Carandini, M., Heeger, D. J., & Movshon, J. A. (1997) · Journal of Neuroscience · doi:10.1523/jneurosci.17-21-08621.1997 · Cited by 926 · see citing works
Handbook of Parametric and Nonparametric Statistical Procedures
Sheskin, D. J. (1996) · CRC Press eBooks · doi:10.4324/9780203489536 · Cited by 914 · see citing works
A no-reference objective image sharpness metric based on the notion of just noticeable blur (JNB)
Ferzli, R., & Karam, L. J. (2009) · IEEE Transactions on Image Processing · doi:10.1109/tip.2008.2011760 · Cited by 758 · see citing works
A New SURE Approach to Image Denoising: Interscale Orthonormal Wavelet Thresholding
Luisier, F., Blu, T., & Unser, M. (2007) · IEEE Transactions on Image Processing · doi:10.1109/tip.2007.891064 · Cited by 623 · see citing works
No-reference quality assessment using natural scene statistics: JPEG2000
Sheikh, H. R., Bovik, A. C., & Cormack, L. (2005) · IEEE Transactions on Image Processing · doi:10.1109/tip.2005.854492 · Cited by 575 · see citing works
Self-citationSharifi, K., & Leon-Garcia, A. (1995) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/76.350779 · Cited by 540 · see citing works
On Advances in Statistical Modeling of Natural Images
Srivastava, A., Lee, A. B., Simoncelli, E. P., & Zhu, S. (2003) · Journal of Mathematical Imaging and Vision · doi:10.1023/a:1021889010444 · Cited by 483 · see citing works
(1993) · Cited by 466 · see citing works
Automatic Parameter Selection for Denoising Algorithms Using a No-Reference Measure of Image Content
Zhu, X., & Milanfar, P. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2010.2052820 · Cited by 380 · see citing works
RRED Indices: Reduced Reference Entropic Differencing for Image Quality Assessment
Soundararajan, R., & Bovik, A. C. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2166082 · Cited by 337 · see citing works
Self-citationReduced-Reference Image Quality Assessment Using Divisive Normalization-Based Image Representation
Li, Q., & Wang, Z. (2009) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2009.2014497 · Cited by 323 · see citing works
Blind image quality assessment through anisotropy
Gabarda, S., & Cristóbal, G. (2007) · Journal of the Optical Society of America A · doi:10.1364/josaa.24.000b42 · Cited by 301 · see citing works
Reduced- and No-Reference Image Quality Assessment
Wang, Z., & Bovik, A. (2011) · IEEE Signal Processing Magazine · doi:10.1109/msp.2011.942471 · Cited by 280 · see citing works
Self-citationNo-Reference Image Quality Assessment Using Visual Codebooks
Ye, P., & Doermann, D. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2190086 · Cited by 272 · see citing works
Learning a blind measure of perceptual image quality
Tang, H., Joshi, N., & Kapoor, A. (2011) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2011.5995446 · Cited by 257 · see citing works
A no-reference perceptual image sharpness metric based on a cumulative probability of blur detection
Narvekar, N. D., & Karam, L. J. (2009) · 2009 International Workshop on Quality of Multimedia Experience · doi:10.1109/qomex.2009.5246972 · Cited by 208 · see citing works
Sparse representation for blind image quality assessment
He, L., Tao, D., Li, X., & Gao, X. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6247795 · Cited by 155 · see citing works
SVD-Based Quality Metric for Image and Video Using Machine Learning
Narwaria, M., & Lin, W. (2011) · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · doi:10.1109/tsmcb.2011.2163391 · Cited by 152 · see citing works
Objective Image Quality Assessment Based on Support Vector Regression
Narwaria, M., & Lin, W. (2010) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2010.2040192 · Cited by 147 · see citing works
Wainwright, M. J., Schwartz, O., & Simoncelli, E. P. (2002) · Cited by 139 · see citing works
Blind image quality assessment
Li, X. (2003) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2002.1038057 · Cited by 138 · see citing works
Multiscale skewed heavy tailed model for texture analysis
Lasmar, N.-E., Stitou, Y., & Berthoumieu, Y. (2009) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2009.5414404 · Cited by 129 · see citing works
A no-reference perceptual image sharpness metric based on saliency-weighted foveal pooling
Sadaka, N. G., Karam, L. J., Ferzli, R. M., & Abousleman, G. P. (2008) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2008.4711768 · Cited by 84 · see citing works
No-reference visually significant blocking artifact metric for natural scene images
Suthaharan, S. (2009) · Signal Processing · doi:10.1016/j.sigpro.2009.02.007 · Cited by 80 · see citing works
Hybrid No-Reference Natural Image Quality Assessment of Noisy, Blurry, JPEG2000, and JPEG Images
Shen, J., Qin, L., & Erlebacher, G. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2108661 · Cited by 74 · see citing works
Varadarajan, S., & Karam, L. J. (2008) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2008.4711776 · Cited by 59 · see citing works
Nuttall, A. H. (1983) · doi:10.21236/ada133703 · Cited by 29 · see citing works
A No-Reference Blocking Artifacts Metric Using Selective Gradient and Plainness Measures
Chen, J., Zhang, Y., Liang, L., Ma, S., Wang, R., & Gao, W. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-89796-5_108 · Cited by 23 · see citing works
A two-stage framework for blind image quality assessment
Moorthy, A. K., & Bovik, A. C. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5651745 · Cited by 21 · see citing works
Self-citationPerceptual Video Processing: Seeing the Future [Point of View]
Bovik, A. C. (2010) · Proceedings of the IEEE · doi:10.1109/jproc.2010.2068371 · Cited by 19 · see citing works
Self-citationReference free quality metric using a region-based attention model for JPEG-2000 compressed images
Barland, R., & Saadane, A. (2006) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.642933 · Cited by 15 · see citing works
Flagged first, then by citations
Research works printed but not linked: 7
- wainwright, 2002, Statist Theories of the Brain, 203
- 10.1088/0954-898x/5/4/006 · DOI
- saad, 2012, BLIINDS Code
- moorthy, 2011, DIIVINE Code Implementation
- girod, 1993, Visual Factors of Electronic Image Communications, 207
- wang, 2003, MS-SSIM Code
- wang, 2004, SSIM Code
Cited by
Sorted by citations
Making a “Completely Blind” Image Quality Analyzer
Mittal, A., Soundararajan, R., & Bovik, A. C. (2013) · IEEE Signal Processing Letters · doi:10.1109/lsp.2012.2227726 · Cited by 6,766 · see citing works
Self-citationBenchmarking Single-Image Dehazing and Beyond
Li, B., Ren, W., Fu, D., Tao, D., Feng, D., Zeng, W., & Wang, Z. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2867951 · Cited by 2,376 · see citing works
A Feature-Enriched Completely Blind Image Quality Evaluator
Zhang, L., Zhang, L., & Bovik, A. C. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2426416 · Cited by 1,311 · see citing works
Self-citationConvolutional Neural Networks for No-Reference Image Quality Assessment
Kang, L., Ye, P., Li, Y., & Doermann, D. (2014) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2014.224 · Cited by 1,308 · see citing works
Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment
Bosse, S., Maniry, D., Muller, K.-R., Wiegand, T., & Samek, W. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2760518 · Cited by 1,263 · see citing works
Underwater Image Restoration Based on Image Blurriness and Light Absorption
Peng, Y., & Cosman, P. C. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2663846 · Cited by 1,258 · see citing works
Talebi, H., & Milanfar, P. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2831899 · Cited by 1,194 · see citing works
MUSIQ: Multi-scale Image Quality Transformer
Ke, J., Wang, Q., Wang, Y., Milanfar, P., & Yang, F. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00510 · Cited by 1,048 · see citing works
The Perception-Distortion Tradeoff
Blau, Y., & Michaeli, T. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00652 · Cited by 1,001 · see citing works
Blind image quality evaluation using perception based features
Venkatanath, N., Praneeth, D., Bh, M. C., Channappayya, S. S., & Medasani, S. S. (2015) · National Conference on Communications · doi:10.1109/ncc.2015.7084843 · Cited by 998 · see citing works
Blind Image Quality Assessment Using a Deep Bilinear Convolutional Neural Network
Zhang, W., Ma, K., Yan, J., Deng, D., & Wang, Z. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2018.2886771 · Cited by 970 · see citing works
Real-World Underwater Enhancement: Challenges, Benchmarks, and Solutions Under Natural Light
Liu, R., Fan, X., Zhu, M. B., Hou, M., & Luo, Z. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2963772 · Cited by 911 · see citing works
Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network
Su, S., Yan, Q., Zhu, Y., Zhang, C., Ge, X., Sun, J., & Zhang, Y. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00372 · Cited by 899 · see citing works
Referenceless Prediction of Perceptual Fog Density and Perceptual Image Defogging
Choi, L. K., You, J., & Bovik, A. C. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2456502 · Cited by 867 · see citing works
Self-citationO-HAZE: A Dehazing Benchmark with Real Hazy and Haze-Free Outdoor Images
Ancuti, C. O., Ancuți, C., Timofte, R., & Vleeschouwer, C. D. (2018) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00119 · Cited by 819 · see citing works
Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation
Caballero, J., Ledig, C., Aitken, A. P., Acosta, A., Totz, J., Wang, Z., & Shi, W. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.304 · Cited by 799 · see citing works
Exploring CLIP for Assessing the Look and Feel of Images
Wang, J., Chan, K. C. K., & Loy, C. C. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i2.25353 · Cited by 795 · see citing works
Waterloo Exploration Database: New Challenges for Image Quality Assessment Models
Ma, K., Duanmu, Z., Wu, Q., Wang, Z., Yong, H., Li, H., & Zhang, L. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2631888 · Cited by 789 · see citing works
Massive Online Crowdsourced Study of Subjective and Objective Picture Quality
Ghadiyaram, D., & Bovik, A. C. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2500021 · Cited by 782 · see citing works
Self-citationKonIQ-10k: An Ecologically Valid Database for Deep Learning of Blind Image Quality Assessment
Hosu, V., Lin, H., Sziranyi, T., & Saupe, D. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2967829 · Cited by 759 · see citing works
No-reference image quality assessment based on spatial and spectral entropies
Liu, L., Liu, B., Huang, H., & Bovik, A. C. (2014) · Signal Processing Image Communication · doi:10.1016/j.image.2014.06.006 · Cited by 724 · see citing works
Self-citationPerceptual image quality assessment: a survey
Zhai, G., & Min, X. (2020) · Science China Information Sciences · doi:10.1007/s11432-019-2757-1 · Cited by 662 · see citing works
Blind Image Quality Assessment Using Joint Statistics of Gradient Magnitude and Laplacian Features
Xue, W., Mou, X., Zhang, L., Bovik, A. C., & Feng, X. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2355716 · Cited by 641 · see citing works
Self-citationPerception and sensing for autonomous vehicles under adverse weather conditions: A survey
Zhang, Y., Carballo, A., Yang, H., & Takeda, K. (2023) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2022.12.021 · Cited by 640 · see citing works
AdaFace: Quality Adaptive Margin for Face Recognition
Kim, M., Jain, A. K., & Liu, X. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.01819 · Cited by 620 · see citing works
End-to-End Blind Image Quality Assessment Using Deep Neural Networks
Ma, K., Liu, W., Zhang, K., Duanmu, Z., Wang, Z., & Zuo, W. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2774045 · Cited by 613 · see citing works
Learning a no-reference quality metric for single-image super-resolution
Ma, C., Yang, C., Yang, X., & Yang, M. (2017) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2016.12.009 · Cited by 609 · see citing works
The 2018 PIRM Challenge on Perceptual Image Super-Resolution
Blau, Y., Mechrez, R., Timofte, R., Michaeli, T., & Zelnik‐Manor, L. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11021-5_21 · Cited by 609 · see citing works
Using Free Energy Principle For Blind Image Quality Assessment
Gu, K., Zhai, G., Yang, X., & Zhang, W. (2014) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2014.2373812 · Cited by 606 · see citing works
Reversible data hiding: Advances in the past two decades
Shi, Y.-Q., Li, X., Zhang, X., Wu, H., & Ma, B. (2016) · IEEE Access · doi:10.1109/access.2016.2573308 · Cited by 598 · see citing works
Learning A Sparse Transformer Network for Effective Image Deraining
Chen, X., Li, H., Li, M., & Pan, J. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00571 · Cited by 581 · see citing works
MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment
Yang, S., Wu, T., Shi, S., Lao, S., Gong, Y., Cao, M., Wang, J., & Yang, Y. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00126 · Cited by 554 · see citing works
RankIQA: Learning from Rankings for No-Reference Image Quality Assessment
Liu, X., van de Weijer, J., & Bagdanov, A. D. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.118 · Cited by 543 · see citing works
KADID-10k: A Large-scale Artificially Distorted IQA Database
Lin, H., Hosu, V., & Saupe, D. (2019) · 2019 Eleventh International Conference on Quality of Multimedia Experience (QoMEX) · doi:10.1109/qomex.2019.8743252 · Cited by 523 · see citing works
Blind Image Quality Estimation via Distortion Aggravation
Min, X., Zhai, G., Gu, K., Liu, Y., & Yang, X. (2018) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2018.2816783 · Cited by 518 · see citing works
NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Images
Ancuti, C. O., Ancuti, C., & Timofte, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00230 · Cited by 517 · see citing works
“Due to this limitation, earlier dehazing quality metrics were restricted to non-reference image quality metrics (NRIQA) [30, 31, 36].”
BackgroundBlind Image Quality Assessment Based on High Order Statistics Aggregation
Xu, J., Ye, P., Li, Q., Du, H., Liu, Y., & Doermann, D. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2585880 · Cited by 490 · see citing works
A Deep Journey into Super-resolution
Anwar, S., Khan, S. H., & Barnes, N. M. (2020) · ACM Computing Surveys · doi:10.1145/3390462 · Cited by 483 · see citing works
MetaIQA: Deep Meta-Learning for No-Reference Image Quality Assessment
Zhu, H., Li, L., Wu, J., Dong, W., & Shi, G. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01415 · Cited by 467 · see citing works
No-Reference Image Quality Assessment via Transformers, Relative Ranking, and Self-Consistency
Golestaneh, S. A., Dadsetan, S., & Kitani, K. M. (2022) · 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv51458.2022.00404 · Cited by 465 · see citing works
I-HAZE: A Dehazing Benchmark with Real Hazy and Haze-Free Indoor Images
Ancuți, C., Ancuti, C. O., Timofte, R., & Vleeschouwer, C. D. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01449-0_52 · Cited by 458 · see citing works
Fully Deep Blind Image Quality Predictor
Kim, J., & Lee, S. (2016) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2016.2639328 · Cited by 455 · see citing works
Blind Quality Assessment Based on Pseudo-Reference Image
Min, X.-K., Gu, K., Zhai, G.-T., Liu, J., Yang, X.-K., & Chen, C. W. (2018) · IEEE transactions on multimedia · doi:10.1109/tmm.2017.2788206 · Cited by 426 · see citing works
Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data
Gu, K., Tao, D., Qiao, J., & Lin, W. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2649101 · Cited by 449 · see citing works
A Comparative Study for Single Image Blind Deblurring
Lai, W., Huang, J., Hu, Z., Ahuja, N., & Yang, M. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.188 · Cited by 446 · see citing works
Seven Challenges in Image Quality Assessment: Past, Present, and Future Research
Chandler, D. M. (2013) · ISRN Signal Processing · doi:10.1155/2013/905685 · Cited by 427 · see citing works
Song, W., Wang, Y., Huang, D., & Tjondronegoro, D. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00776-8_62 · Cited by 419 · see citing works
Deep Image Deblurring: A Survey
Zhang, K., Ren, W., Luo, W., Lai, W., Stenger, B., Yang, M., & Li, H. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01633-5 · Cited by 408 · see citing works
From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality
Ying, Z., Niu, H., Gupta, P., Mahajan, D., Ghadiyaram, D., & Bovik, A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00363 · Cited by 406 · see citing works
Self-citationPSD: Principled Synthetic-to-Real Dehazing Guided by Physical Priors
Chen, Z., Wang, Y., Yang, Y., & Liu, D. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00710 · Cited by 394 · see citing works
The Analysis of Image Contrast: From Quality Assessment to Automatic Enhancement
Gu, K., Zhai, G., Lin, W., & Liu, M. (2015) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2401732 · Cited by 390 · see citing works
Quality Assessment of In-the-Wild Videos
Li, D., Jiang, T., & Jiang, M. (2019) · Proceedings of the 27th ACM International Conference on Multimedia · doi:10.1145/3343031.3351028 · Cited by 387 · see citing works
Perceptual Quality Assessment of Smartphone Photography
Fang, Y., Zhu, H., Zeng, Y., Ma, K., & Wang, Z. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00373 · Cited by 387 · see citing works
No-Reference Quality Metric of Contrast-Distorted Images Based on Information Maximization
Gu, K., Lin, W., Zhai, G., Yang, X., Zhang, W., & Chen, C. W. (2016) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2016.2575544 · Cited by 373 · see citing works
An Experiment-Based Review of Low-Light Image Enhancement Methods
Wang, W., Wu, X., Yuan, X., & Gao, Z. (2020) · IEEE Access · doi:10.1109/access.2020.2992749 · Cited by 373 · see citing works
Blind Image Quality Assessment via Deep Learning
Hou, W., Gao, X., Tao, D., & Li, X. (2014) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2014.2336852 · Cited by 370 · see citing works
UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content
Tu, Z., Wang, Y., Birkbeck, N., Adsumilli, B., & Bovik, A. C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3072221 · Cited by 363 · see citing works
“We also avoid using duplicate features in different models, such as the BRISQUE-like features in HIGRADE, and the C-DIIVINE features in V-BLIINDS.”
MethodInfluentialSelf-citationSong, W., Wang, Y., Huang, D., Liotta, A., & Perra, C. (2020) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2019.2960942 · Cited by 361 · see citing works
D-HAZY: A dataset to evaluate quantitatively dehazing algorithms
Ancuți, C., Ancuti, C. O., & Vleeschouwer, C. D. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532754 · Cited by 360 · see citing works
Benchmarking Low-Light Image Enhancement and Beyond
Liu, J., Xu, D., Yang, W., Fan, M., & Huang, H. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01418-8 · Cited by 359 · see citing works
A Completely Blind Video Integrity Oracle
Mittal, A., Saad, M. A., & Bovik, A. C. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2502725 · Cited by 357 · see citing works
Self-citationTwo-Level Approach for No-Reference Consumer Video Quality Assessment
Korhonen, J. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2923051 · Cited by 354 · see citing works
dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs
Ma, K., Liu, W., Liu, T., Wang, Z., & Tao, D. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2708503 · Cited by 354 · see citing works
Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild
Zhang, W., Ma, K., Zhai, G., & Yang, X. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3061932 · Cited by 353 · see citing works
On the use of deep learning for blind image quality assessment
Bianco, S., Celona, L., Napoletano, P., & Schettini, R. (2017) · Signal Image and Video Processing · doi:10.1007/s11760-017-1166-8 · Cited by 348 · see citing works
Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective
Zhang, W., Zhai, G., Wei, Y., Yang, X., & Ma, K. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01352 · Cited by 347 · see citing works
No-Reference Quality Assessment of Contrast-Distorted Images Based on Natural Scene Statistics
Fang, Y., Ma, K., Wang, Z., Lin, W., Fang, Z., & Zhai, G. (2014) · IEEE Signal Processing Letters · doi:10.1109/lsp.2014.2372333 · Cited by 343 · see citing works
Objective quality assessment of multiply distorted images
Jayaraman, D., Mittal, A., Moorthy, A. K., & Bovik, A. C. (2012) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/acssc.2012.6489321 · Cited by 337 · see citing works
Self-citationUnified Blind Quality Assessment of Compressed Natural, Graphic, and Screen Content Images
Min, X.-K., Ma, K.-D., Gu, K., Zhai, G.-T., Wang, Z., & Lin, W.-S. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2735192 · Cited by 271 · see citing works
Deep CNN-Based Blind Image Quality Predictor
Kim, J., Nguyen, D. C., & Lee, S. (2018) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2018.2829819 · Cited by 330 · see citing works
Image super-resolution: A comprehensive review, recent trends, challenges and applications
Lepcha, D. C., Goyal, B., Dogra, A., & Goyal, V. (2022) · Information Fusion · doi:10.1016/j.inffus.2022.10.007 · Cited by 323 · see citing works
Perceptual quality prediction on authentically distorted images using a bag of features approach
Ghadiyaram, D., & Bovik, A. C. (2017) · Journal of Vision · doi:10.1167/17.1.32 · Cited by 322 · see citing works
Self-citationNo-Reference Image Sharpness Assessment in Autoregressive Parameter Space
Gu, K., Zhai, G., Lin, W., Yang, X., & Zhang, W. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2439035 · Cited by 317 · see citing works
Wang, Y., Song, W., Fortino, G., Qi, L., Zhang, W., & Liotta, A. (2019) · IEEE Access · doi:10.1109/access.2019.2932130 · Cited by 316 · see citing works
Large-Scale Study of Perceptual Video Quality
Sinno, Z., & Bovik, A. C. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2869673 · Cited by 310 · see citing works
Self-citationContrastive Semi-Supervised Learning for Underwater Image Restoration via Reliable Bank
Huang, S., Wang, K., Liu, H., Chen, J., & Li, Y. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01740 · Cited by 305 · see citing works
Image Quality Assessment Using Contrastive Learning
Madhusudana, P. C., Birkbeck, N., Wang, Y., Adsumilli, B., & Bovik, A. C. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3181496 · Cited by 295 · see citing works
Self-citationTOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment
Chen, C., Mo, J., Hou, J., Wu, H., Liao, L., Sun, W., Yan, Q., & Lin, W. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3378466 · Cited by 291 · see citing works
Image Sharpness Assessment Based on Local Phase Coherence
Hassen, R., Wang, Z., & Salama, M. M. A. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2251643 · Cited by 289 · see citing works
Blind image quality assessment by relative gradient statistics and adaboosting neural network
Liu, L., Hua, Y., Zhao, Q., Huang, H., & Bovik, A. C. (2015) · Signal Processing Image Communication · doi:10.1016/j.image.2015.10.005 · Cited by 283 · see citing works
Self-citationKim, J., Zeng, H., Ghadiyaram, D., Lee, S., Zhang, L., & Bovik, A. C. (2017) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2736018 · Cited by 283 · see citing works
Self-citationLightening Network for Low-Light Image Enhancement
Wang, L.-W., Liu, Z.-S., Siu, W.-C., & Lun, D. P.-K. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3008396 · Cited by 281 · see citing works
Objective Quality Evaluation of Dehazed Images
Min, X., Zhai, G., Gu, K., Yang, X., & Guan, X. (2018) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2018.2868771 · Cited by 275 · see citing works
Hallucinated-IQA: No-Reference Image Quality Assessment via Adversarial Learning
Lin, K.-Y., & Wang, G. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00083 · Cited by 274 · see citing works
No-Reference Image Blur Assessment Based on Discrete Orthogonal Moments
Li, L., Lin, W., Wang, X., Yang, G., Bahrami, K., & Kot, A. C. (2015) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2392129 · Cited by 272 · see citing works
Deep Learning of Human Visual Sensitivity in Image Quality Assessment Framework
Kim, J., & Lee, S. (2017) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2017.213 · Cited by 270 · see citing works
Underwater Image Enhancement Quality Evaluation: Benchmark Dataset and Objective Metric
Jiang, Q., Gu, Y., Li, C., Cong, R., & Shao, F. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3164918 · Cited by 270 · see citing works
Low-Light Image Enhancement with Wavelet-Based Diffusion Models
Jiang, H., Luo, A., Fan, H., Han, S., & Liu, S. (2023) · ACM Transactions on Graphics · doi:10.1145/3618373 · Cited by 267 · see citing works
Review of medical image quality assessment
Chow, L. S., & Paramesran, R. (2016) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2016.02.006 · Cited by 266 · see citing works
FAST-VQA: Efficient End-to-End Video Quality Assessment with Fragment Sampling
Wu, H., Chen, C., Hou, J., Liao, L., Wang, A., Sun, W., Yan, Q., & Lin, W. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20068-7_31 · Cited by 264 · see citing works
Multi-frame Quality Enhancement for Compressed Video
Yang, R., Xu, M., Wang, Z., & Li, T. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00697 · Cited by 256 · see citing works
Quality Evaluation of Image Dehazing Methods Using Synthetic Hazy Images
Min, X., Zhai, G., Gu, K., Zhu, Y., Zhou, J., Guo, G., Yang, X., Guan, X., & Zhang, W. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2902097 · Cited by 256 · see citing works
UCL-Dehaze: Toward Real-World Image Dehazing via Unsupervised Contrastive Learning
Wang, Y., Yan, X., Wang, F. L., Xie, H., Yang, W., Zhang, X.-P. S., Qin, J., & Wei, M. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3362153 · Cited by 255 · see citing works
A Deep Learning based No-reference Quality Assessment Model for UGC Videos
Sun, W., Min, X., Lu, W., & Zhai, G. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3548329 · Cited by 253 · see citing works
Low-Light Image Enhancement via Progressive-Recursive Network
Li, J., Feng, X., & Hua, Z. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3049940 · Cited by 249 · see citing works
Screen Content Quality Assessment: Overview, Benchmark, and Beyond
Min, X., Gu, K., Zhai, G., Yang, X., Zhang, W., Callet, P. L., & Chen, C. W. (2021) · ACM Computing Surveys · doi:10.1145/3470970 · Cited by 249 · see citing works
Bringing Old Photos Back to Life
Wan, Z., Zhang, B., Chen, D., Zhang, P., Chen, D., Liao, J., & Wen, F. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00282 · Cited by 245 · see citing works
Musallam, A. S., Sobhy, A., & Hussein, M. K. (2022) · IEEE Access · doi:10.1109/access.2022.3140289 · Cited by 243 · see citing works
A Perception-Aware Decomposition and Fusion Framework for Underwater Image Enhancement
Kang, Y., Jiang, Q., Li, C., Ren, W., Liu, H., & Wang, P. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3208100 · Cited by 243 · see citing works
Gu, K., Wang, S., Zhai, G., Ma, S., Yang, X., Lin, W., Zhang, W., & Gao, W. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2518868 · Cited by 241 · see citing works
- Authors
- Mittal, A., Moorthy, A. K., & Bovik, A. C.
- Affiliations
- The University of Texas at Austin (US)
- ORCID
- Bovik, A. C.
- Venue
- IEEE Transactions on Image Processing
- Published
- 2012-12
- Volume
- 21
- Issue
- 12
- Pages
- 4695-4708
- ISSN
- 1057-7149 (ISSN-L)
- 1941-0042
- OpenAlex
- W1982471090
- Semantic Scholar
- a2cad4e4fd946adf6cc87e483b2ba18579de1264
- Cited by
- 6,064
- References
- 56
- Citations by year
- 2026: 652 · 2025: 861 · 2024: 758 · 2023: 707 · 2022: 645 · 2021: 490 · 2020: 426 · 2019: 387 · 2018: 334 · 2017: 268 · 2016: 208 · 2015: 151 · 2014: 129 · 2013: 42 · 2012: 5
- FWCI
- 107.73
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Image Processing (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Video Quality Assessment
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Keywords
- no-reference image quality assessment, BRISQUE, natural scene statistics, spatial domain features, blind image denoising
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-09.
Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-09.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
