Making a “Completely Blind” Image Quality Analyzer
The DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Abstract
An important aim of research on the blind image quality assessment (IQA) problem is to devise perceptual models that can predict the quality of distorted images with as little prior knowledge of the images or their distortions as possible. Current state-of-the-art “general purpose” no reference (NR) IQA algorithms require knowledge about anticipated distortions in the form of training examples and corresponding human opinion scores. However we have recently derived a blind IQA model that only makes use of measurable deviations from statistical regularities observed in natural images, without training on human-rated distorted images, and, indeed without any exposure to distorted images. Thus, it is “completely blind.” The new IQA model, which we call the Natural Image Quality Evaluator (NIQE) is based on the construction of a “quality aware” collection of statistical features based on a simple and successful space domain natural scene statistic (NSS) model. These features are derived from a corpus of natural, undistorted images. Experimental results show that the new index delivers performance comparable to top performing NR IQA models that require training on large databases of human opinions of distorted images. A software release is available at http://live.ece.utexas.edu/research/quality/niqe_release.zip.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
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 · cited 4×
“We compared NIQE with three FR indices: PSNR, SSIM [9] and multiscale SSIM (MS-SSIM) [18], five general purpose OA-DA algorithms - CBIQ [6], LBIQ [7], BLIINDS-II [5], DIIVINE [4], BRISQUE [3] and the DA-OU approach TMIQ [8].”
BackgroundMethodSelf-citationBook Review: Pattern Recognition and Machine Learning
Nasrabadi, N. M. (2007) · Journal of Electronic Imaging · doi:10.1117/1.2819119 · Cited by 22,066 · cited 1×
“, xk) are the NSS features computed in (5)(8), and ν and Σ denote the mean and covariance matrix of the MVG model, which are estimated using a standard maximum likelihood estimation procedure [16].”
MethodPattern Recognition and Machine Learning
(2006) · doi:10.1007/978-0-387-45528-0 · Cited by 9,824
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 · cited 1×
“Images were selected from copyright free Flickr data and from the Berkeley image segmentation database [17] making sure that no overlap occurs with the test image content.”
MethodMultiscale 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 · cited 1×
“We compared NIQE with three FR indices: PSNR, SSIM [9] and multiscale SSIM (MS-SSIM) [18], five general purpose OA-DA algorithms - CBIQ [6], LBIQ [7], BLIINDS-II [5], DIIVINE [4], BRISQUE [3] and the DA-OU approach TMIQ [8].”
MethodSelf-citationNo-Reference Image Quality Assessment in the Spatial Domain
Mittal, A., Moorthy, A. K., & Bovik, A. C. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2214050 · Cited by 6,064 · cited 6×
“above, their statistics are characterized by ‘quality aware’ NSS features computed from each selected patch [3].”
BackgroundMethodSelf-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 2,966 · cited 3×
“The NIQE scores are passed through a logistic non-linearity [2] before computing LCC for mapping to DMOS space.”
BackgroundMethodSelf-citationPattern recognition and machine learning
(2007) · Choice Reviews Online · doi:10.5860/choice.44-5091 · Cited by 2,650
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 · cited 3×
“Existing general purpose NR IQA algorithms are based on models that can learn to predict human judgments of image quality from databases of human-rated distorted images [3], [4], [5], [6], [7].”
BackgroundMethodSelf-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 1,751 · cited 3×
“Existing general purpose NR IQA algorithms are based on models that can learn to predict human judgments of image quality from databases of human-rated distorted images [3], [4], [5], [6], [7].”
BackgroundMethodSelf-citation
Research works printed but not linked: 1
- 2012, Image obsessed, National Geographic, 221, 35
Cited by
Items 901–1,000 of 1,013
SteReFo: Efficient Image Refocusing with Stereo Vision
Busam, B., Hog, M., McDonagh, S., & Slabaugh, G. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00411 · Cited by 47
“In order to provide quantitative evaluation of our results, in addition to classical metrics, we propose to utilize a perceptual metric commonly used by the super resolution community [7, 6], the NIQE score [34].”
BackgroundMethodMulti-Pooled Inception Features for No-Reference Image Quality Assessment
Varga, D. (2020) · Applied Sciences · doi:10.3390/app10062186 · Cited by 47
“To compare our proposed method to other state-of-the-art algorithms, we collected ten traditional learning-based NR-IQA metrics ( DIIVINE [2], BLIINDS-II [45], BRISQUE [6], CurveletQA [4], SSEQ [46], GRAD-LOG-CP [47], BMPRI [48], SPF-IQA [49], SCORER [50], ENIQA [51] ), and two opinion-unaware method (NIQE [52], PIQE…”
MethodA Subjective and Objective Study of Space-Time Subsampled Video Quality
Lee, D. Y., Paul, S., Bampis, C. G., Ko, H., Kim, J.-H., Jeong, S., Homan, B., & Bovik, A. C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3137658 · Cited by 47
“The no-reference models that we evaluated include BRISQUE [37] and NIQE [38], which are NSS-based, and TLVQM [39], which is a learning-based model that uses a large set of hand-designed features, including motion statistics and estimates of specific distortions.”
MethodSelf-citationPixel-Wise Wasserstein Autoencoder for Highly Generative Dehazing
Kim, G., Park, S., & Kwon, J. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3084743 · Cited by 47
“Table III shows numerical results for WCT 2 and pWAE in terms of no-reference image quality metrics, i . e ., the naturalness image quality evaluator (NIQE) [49], and perceptual index (PI) [50].”
BackgroundPrajapati, K., Chudasama, V. M., Patel, H., Upla, K. P., Raja, K. B., Ramachandra, R., & Busch, C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3113783 · Cited by 47
Wang, G., Li, W., Gao, X., Xiao, B., & Du, J. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.01.059 · Cited by 47
Acharya, U. K., & Kumar, S. (2022) · Multidimensional Systems and Signal Processing · doi:10.1007/s11045-022-00853-9 · Cited by 47
“Its value should be close to one NIQE (Mittal et al., 2012) D = √( (v1 − v2)T ( ( ∑ 1 − ∑ 2) 2 )−1 (v1 − v2) ) It measures the distance between the multivariate Gaussian (MVG) fit to the features extracted from the distorted image and natural scene statistic (NSS) feature model.”
BackgroundMethodInfluentialHuman Perceptual Quality Driven Underwater Image Enhancement Framework
Li, M., Lin, Y., Shen, L., Wang, Z., Wang, K., & Wang, Z. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3223083 · Cited by 47
“…such as perceptual index (PI) [12], natural image quality evaluator (NIQE) [22], blind/referenceless image spatial quality eval-uator (BRISQUE) [21], underwater image quality measure (UIQM) [27] and underwater color image quality evaluation (UCIQE) [24] are not differentiable because they…”
BackgroundMethodAdaptive Deep PnP Algorithm for Video Snapshot Compressive Imaging
Wu, Z., Yang, C., Su, X., & Yuan, X. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-023-01777-y · Cited by 47
BBAND INDEX: A NO-REFERENCE BANDING ARTIFACT PREDICTOR
Tu, Z., Lin, J., Wang, Y., Adsumilli, B., & Bovik, A. C. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9053634 · Cited by 46
“In this paper we propose a new, “completely blind” [19] banding model, dubbed the B lind BAN ding Artifact D etector (BBAND index), by leveraging edge detection and a human visual model.”
MethodSelf-citationLow-Light Stereo Image Enhancement
Huang, J., Fu, X., Xiao, Z., Zhao, F., & Xiong, Z. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3154152 · Cited by 47
“…normal exposure images, we follow selection rules containing several steps including lightness estimation, blur estimation, colorful estimation and naturalness estimation, which are set according to the mean value, edge variance, color variance, and NIQE [54] of the image, respectively.”
MethodDiffBFR: Bootstrapping Diffusion Model for Blind Face Restoration
Qiu, X., Han, C., Zhang, Z., Li, B., Guo, T., & Nie, X. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3611731 · Cited by 46
Ultrahigh-Resolution Reconstruction of Shale Digital Rocks from FIB-SEM Images Using Deep Learning
Liang, Y., Wang, S., Feng, Q., Zhang, M., Cao, X., & Wang, X. (2023) · SPE Journal · doi:10.2118/218397-pa · Cited by 46
Perceptual Quality Assessment of NeRF and Neural View Synthesis Methods for Front‐Facing Views
Liang, H., Wu, T., Hanji, P., Banterle, F., Gao, H., Mantiuk, R., & Öztireli, C. (2024) · Computer Graphics Forum · doi:10.1111/cgf.15036 · Cited by 46
“We test LPIPS using two different backbone models, VGG and AlexNet, [44] on information-theoretic setting FSIM ✓ ✗ Low-level image feature similarity [63] based on the human visual system LPIPS-VGG ✓ ✗ Perceptual similarity metric based on [64] deep network of VGG model LPIPS-ALEX ✓ ✗ Perceptual similarity metric base…”
BackgroundMethodInfluentialFDNet: Fourier transform guided dual-channel underwater image enhancement diffusion network
Zhu, Z., Li, X., Ma, Q., Zhai, J., & Hu, H. (2024) · Science China Technological Sciences · doi:10.1007/s11431-024-2824-x · Cited by 46
Personalized Generation In Large Model Era: A Survey
Xu, Y., Zhang, J., Salemi, A., Hu, X., Wang, W., Feng, F., Zamani, H., He, X., & Chua, T. (2025) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2025.acl-long.1201 · Cited by 46
Wu, Q., Li, H., Meng, F., Ngan, K. N., & Zhu, S. (2015) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2015.08.009 · Cited by 46
“Some possible solutions have been discussed in [64,29].”
BackgroundMethodUtilizing Dictionary Learning and Machine Learning for Blind Quality Assessment of 3-D Images
Zhou, W., Qiu, W., & Wu, M. (2017) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2016.2638620 · Cited by 46
“These included four FR metrics (the classical SSIM [6], FSIM [7], FI [9], and Chen’s metric [10]) and six NR metrics (BRISQUE [18], NIQE [19], QAC [20], IL_NIQE [22], Xue’s metric [26], and Zhou’s metric [32]).”
MethodInfluentialNo-Reference Quality Assessment of Deblurred Images Based on Natural Scene Statistics
Li, L., Yan, Y., Lu, Z., Wu, J., Gu, K., & Wang, S. (2017) · IEEE Access · doi:10.1109/access.2017.2661858 · Cited by 46
“In this part, we compare the proposed metric with the state-of-the-art general-purpose NR image quality metrics, including BIQI [48], DIIVINE [49], BLIINDS-II [50], BRISQUE [51], NIQE [52], DESIQUE [29], CORNIA [53] and NFERM [54].”
A High-Definition Diversity-Scene Database for Image Quality Assessment
Liu, T.-J., Liu, H., Pei, S., & Liu, K.-H. (2018) · IEEE Access · doi:10.1109/access.2018.2864514 · Cited by 46
“FRIQUEE [51] ranks the first for seven distortion types, including Brightness change, Color distortion, Contrast change, Fast fading, JPEG, JPEG2000, and Motion blur, while NIQE [46] only has the excellent performance on Scaling distortion.”
BackgroundMethodHyperspectral Image Denoising by Fusing the Selected Related Bands
Zheng, X., Yuan, Y., & Lu, X. (2018) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2875304 · Cited by 46
“Both Q-metric [47] and NIQE [48] are computed on each denoised spectral band.”
MethodInfluentialA novel image scaling based reversible watermarking scheme for secure medical image transmission
Manikandan, V. M., & Masilamani, V. (2020) · ISA Transactions · doi:10.1016/j.isatra.2020.08.019 · Cited by 46
Comparative study of the methodologies used for subjective medical image quality assessment
Lévêque, L., Outtas, M., Liu, H., & Zhang, L. (2021) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ac1157 · Cited by 46
“An objective assessment was also performed with three FR metrics, i.e., PSNR [22], SSIM [23], and VIF [25], as well as three NR metrics, i.e., BRISQUE [81], NIQE [41], and VIIDEO [87].”
InfluentialCycle Structure and Illumination Constrained GAN for Medical Image Enhancement
Ma, Y., Liu, Y., Cheng, J. T., Zheng, Y., Ghahremani, M., Chen, H., Liu, J., & Zhao, Y. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-59713-9_64 · Cited by 46
Chai, X., Shao, F., Jiang, Q., Meng, X., & Ho, Y. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3112120 · Cited by 46
From Continuity to Editability: Inverting GANs with Consecutive Images
Xu, Y., Du, Y., Xiao, W., Xu, X., & He, S. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01365 · Cited by 46
Unsupervised Image Deraining: Optimization Model Driven Deep CNN
Yu, C., Chang, Y., Li, Y., Zhao, X.-L., & Yan, L. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475441 · Cited by 46
“For real-world images, we employ the non-reference NIQE [25] and user studies to quantitatively evaluate the visual quality of deraining results.”
Li, N., Teurnier, B. L., Boffety, M., Goudail, F., Zhao, Y., & Pan, Q. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3122085 · Cited by 46
Source-Free Domain Adaptation for Real-World Image Dehazing
Yu, H., Huang, J., Liu, Y., Zhu, Q., Zhou, M., & Zhao, F. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3548410 · Cited by 46
“For quantitative comparison of the unlabeled dataset, we employ two wellknown no-reference image quality assessment indicators: BRISQUE [35] and NIQE [36].”
MethodImage Super-Resolution with Deep Dictionary
Maeda, S. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19800-7_27 · Cited by 46
Dual-tree complex wavelet transform and SVD based medical image resolution enhancement
Iqbal, M. Z., Ghafoor, A., Siddiqui, A. M., Riaz, M. M., & Khalid, U. (2014) · Signal Processing · doi:10.1016/j.sigpro.2014.05.011 · Cited by 46
“The PSNR, MSE and SSIM-index of the proposed DTCWT-NLM-SVD-RE cannot be presented because these quantitative comparisons require reference images which are not available after CE so we present only the completely blind image quality analyzer NIQE index [11] for comparison.”
BackgroundMethodCorrespondence and Depth-Image Based Rendering a Hybrid Approach for Free-Viewpoint Video
Lipski, C., Klose, F., & Magnor, M. A. (2014) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2302379 · Cited by 46
Extreme Generative Image Compression by Learning Text Embedding from Diffusion ModelsPreprint
Pan, Z., Zhou, X., & Tian, H. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2211.07793 · Cited by 46
“For blind metrics without GT reference, NIQE [37] is the one comparing image statistics with those of undistorted images.”
MethodDeep Blind Synthesized Image Quality Assessment with Contextual Multi-Level Feature Pooling
Wang, X., Wang, K., Yang, B., Li, F. W. B., & Liang, X. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8802943 · Cited by 45
Specular Reflections Detection and Removal for Endoscopic Images Based on Brightness Classification
Nie, C., Xu, C., Li, Z.-P., Chu, L., & Hu, Y. (2023) · Sensors · doi:10.3390/s23020974 · Cited by 45
“Highlight Removal Evaluation Criteria: Considering that the endoscopic highlight dataset lacks real highlight-free ground truth images, we use the No-Reference (NR) image evaluation metric NIQE [40] and Coefficient of Variation (COV) to quantitatively evaluate the proposed inpainting method.”
Low-light image enhancement via adaptive frequency decomposition network
Liang, X., Chen, X., Ren, K., Miao, X., Chen, Z., & Jin, Y. (2023) · Scientific Reports · doi:10.1038/s41598-023-40899-8 · Cited by 45
Zhao, Z., Lin, H., Shi, D., & Zhou, G. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.110025 · Cited by 47
Spike Camera Image Reconstruction Using Deep Spiking Neural Networks
Zhao, R. Q., Xiong, R., Zhang, J., Yu, Z., Zhu, S., Ма, Л., & Huang, T. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3326294 · Cited by 45
“We also use 3 non-reference metrics to assess the results, namely NIQE [34], BRISQUE [35] and CPBD [36].”
MethodRobust Unpaired Image Dehazing via Adversarial Deformation Constraint
Wei, H., Wu, Q., Wu, C., Ngan, K. N., Li, H., Meng, F., & Qiu, H. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3387451 · Cited by 45
“For the estimation of real-world dataset RWHI where ground truth is unavailable, we employ NR-IQA methods, including Natural Image Quality Evaluator (NIQE) [62], and Perception Index (PI) [63].”
MethodSpatial-Frequency Adaptive Remote Sensing Image Dehazing With Mixture of Experts
Shen, H., Ding, H., Zhang, Y., Cong, X., Zhao, Z., & Jiang, X. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3458986 · Cited by 47
“We first present the naturalness image quality evaluator (NIQE [65]) and fog aware density evaluator (FADE [66]) scores that are associated with no-reference perceptual image quality in Table IV, from which we can see that our method gets the lower values, meaning a high-quality output with better…”
MethodHistoformer: Histogram-Based Transformer for Efficient Underwater Image Enhancement
Peng, Y., Chen, Y.-R., Chen, G.-R., & Liao, C.-J. (2024) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2024.3474919 · Cited by 45
HSIGene: A Foundation Model for Hyperspectral Image Generation
Li, P., Cao, X., Tang, D., Xu, S., Bai, X., Zhou, F., & Meng, D. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3610927 · Cited by 45
“Various no-reference image quality assess indexes, including NIQE [58], PI [59], BRISQUE [60], ILNIQE [61], ClipIQA [62] and CNNIQA [63], are utilized to provide a robust assessment of image perceptual quality.”
Learning Structural Regularity for Evaluating Blocking Artifacts in JPEG Images
Li, L., Lin, W., & Zhu, H. (2014) · IEEE Signal Processing Letters · doi:10.1109/lsp.2014.2320743 · Cited by 45
“Recently, several effective general-purpose NR image quality metrics have been reported, including BIQI [19], BLIINDS-II [20], BRISQUE [21] and NIQE [22].”
BackgroundLv, Y., Yu, M., Jiang, G., Shao, F., Peng, Z., & Chen, F. (2016) · Signal Processing Image Communication · doi:10.1016/j.image.2016.07.003 · Cited by 45
Pairwise-Comparison-Based Rank Learning for Benchmarking Image Restoration Algorithms
Hu, B., Li, L., Liu, H., Lin, W., & Qian, J. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2894958 · Cited by 45
“and Laplacian of Gaussian response (GMLOG) [15], QualityAware Clustering (QAC) [16], Natural Image Quality Evaluator (NIQE) [17], and Integrated Local NIQE (ILNIQE) [18].”
BackgroundSubjective and objective quality assessment for image restoration: A critical survey
Hu, B., Li, L., Wu, J., & Qian, J. (2020) · Signal Processing Image Communication · doi:10.1016/j.image.2020.115839 · Cited by 45
StatNet: Statistical Image Restoration for Low-Dose CT using Deep Learning
Choi, K., Lim, J. S., & Kim, S. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2998413 · Cited by 44
“As image quality metrics, peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), averagedlocalbinarypatterns(LBP)[45],andnaturalnessimage qualityevaluator(NIQE)[46]werecalculatedwiththeslicesof the liver region in Fig.”
MethodVP-NIQE: An opinion-unaware visual perception natural image quality evaluator
Wu, L., Zhang, X., Chen, H., Wang, D., & Deng, J. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.08.048 · Cited by 46
Super-resolution guided knowledge distillation for low-resolution image classification
Chen, H., Pei, Y., Zhao, H., & Huang, Y. (2022) · Pattern Recognition Letters · doi:10.1016/j.patrec.2022.02.006 · Cited by 45
Izumi, T., Amagasaki, M., Ishida, K., & Kiyama, M. (2022) · Journal of Water and Climate Change · doi:10.2166/wcc.2022.291 · Cited by 45
Unsupervised Low-light Image Enhancement with Decoupled Networks
Xiong, W., Liu, D., Shen, X., Chen, F., & Luo, J. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956329 · Cited by 45
“Since the URL dataset does not contain ground truth images, we use non-reference image quality assessment methods BRISQUE [46] and NIQE [47] to quantify the visual quality of the results, as shown in Table IV.”
MethodFog Density Estimation and Image Defogging Based on Surrogate Modeling for Optical Depth
Jiang, Y., Sun, C., Yu, Z. K., & Li, Y. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2700720 · Cited by 45
A Comparative Study of Algorithms for Realtime Panoramic Video Blending
Zhu, Z., Lu, J., Wang, M., Zhang, S., Martin, R. R., Liu, H., & Hu, S. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2808766 · Cited by 45
“We used 6 state of the art noreference video quality metrics: BIQI [26], BRISQUE [27], FRIQUEE [28], NIQE [29], SSEQ [30] and VIIDEO [31].”
MethodQu, B., Liang, X., Sun, S., & Gao, W. (2024) · arXiv · doi:10.48550/arxiv.2404.13573 · Cited by 44
“Classic NR-VQA meth-ods adopt handcrafted features as evaluation metrics [3, 15, 16, 29, 35, 40].”
Thermal UAV Image Super-Resolution Guided by Multiple Visible Cues
Zhao, Z., Zhang, Y., Li, C., Xiao, Y., & Tang, J. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3234058 · Cited by 44
“…are not available in this experiment setting, we perform no-reference image quality assessment based on natural image quality evaluator (NIQE) [67], perception based image quality evaluator (PIQE) [68], and blind/referenceless image spatial quality evaluator (BRISQUE) [69], which are widely…”
MethodSaleem, A. I., Paheding, S., Rawashdeh, N. A., Awad, A., & Kaur, N. (2023) · IEEE Access · doi:10.1109/access.2023.3240648 · Cited by 44
“(24-27): 2) NIQE The Naturalness Image Quality Evaluator (NIQE) builds a model to assess the quality of the image by quantifying deviations from statistical regularities that are present in the natural image [17].”
BackgroundRahman, Z.-U., Aamir, M., Ali, Z., Saudagar, A. K. J., AlTameem, A., & Muhammad, K. (2023) · IEEE Systems Journal · doi:10.1109/jsyst.2023.3262593 · Cited by 44
“This study utilized the following quality metrics: lightness order error (LOE) [14], naturalness image quality evaluator (NIQE) [39], visual information fidelity (VIF) [40], structure similarity index measure (SSIM) [41], peak signal-to-noise ratio (PSNR) [42], learned perceptual image patch…”
MethodTowards Compact Single Image Dehazing via Task-related Contrastive Network
Yi, W., Dong, L., Liu, M., Hui, M., Kong, L., & Zhao, Y. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121130 · Cited by 44
Zoom-VQA: Patches, Frames and Clips Integration for Video Quality Assessment
Zhao, K., Yuan, K., Sun, M. B., & Wen, X. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00137 · Cited by 44
Diffusion Posterior Illumination for Ambiguity-Aware Inverse Rendering
Lyu, L., Tewari, A., Habermann, M., Saito, S., Zollhöfer, M., Leimkühler, T., & Theobalt, C. (2023) · ACM Transactions on Graphics · doi:10.1145/3618357 · Cited by 44
“As an additional indicator of naturalness we compute the non-reference HDRmetric PU21-NIQE [Hanji et al. 2022; Mittal et al. 2013].”
MethodRecent advances in image dehazing: Formal analysis to automated approaches
Goyal, B., Dogra, A., Lepcha, D. C., Goyal, V., Alkhayyat, A. H., Chohan, J. S., & Kukreja, V. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.102151 · Cited by 45
No-reference quality assessment of underwater image enhancement
Xiao, Y., Jiang, Q., & Zhou, W. (2023) · Displays · doi:10.1016/j.displa.2023.102586 · Cited by 44
“The NR IQA methods only rely on the distorted image for quality prediction [33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49].”
DiSR-NeRF: Diffusion-Guided View-Consistent Super-Resolution NeRF
Lee, J. L., Li, C., & Lee, G. H. (2024) · 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/cvpr52733.2024.01943 · Cited by 44
“Instead, we follow [8] to use the Naturalness Image Quality Evaluator (NIQE) [29] as a no-reference evaluator to assess the quality of the rendered SR views.”
MethodSuper-NeRF: View-Consistent Detail Generation for NeRF Super-Resolution
Han, Y., Yu, T., Yu, X., Xu, D., Zheng, B., Dai, Z., Yang, C., Wang, Y., & Dai, Q. (2024) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3490840 · Cited by 44
“Also, we investigate the perception evaluation metrics NIQE [35], which reflects the acceptable grade of the generated image details to the human visual perception.”
IQA Vision Transformed: A Survey of Transformer Architectures in Perceptual Image Quality Assessment
Rehman, M. U., Nizami, I. F., Ullah, F., & Hussain, I. (2024) · IEEE Access · doi:10.1109/access.2024.3506273 · Cited by 44
“Opinion-free BIQA approaches can be classified into two groups: clean model-based methods, which do not require human subjective ratings for training, and methods that use objective scores generated by FR-IQA methods to substitute human subjective evaluations [49], [50], [51].”
Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration
Tang, X., Gu, X., He, X., Hu, X., & Sun, J. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3562211 · Cited by 44
“We use PSNR/SSIM for measuring pixel-wise similarity, LPIPS [71]/FID [72] for measuring perceptual deviation, and two well-known non-reference indexes NIQE [73] and PIQE [74] to assess real-world multiple-degradation images.”
MethodCollaborative Decoding Makes Visual Auto-Regressive Modeling Efficient
Chen, Z., Ma, X., Fang, G., & Wang, X. (2025) · 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/cvpr52734.2025.02173 · Cited by 44
Rep-Mamba: Re-Parameterization in Vision Mamba for Lightweight Remote Sensing Image Super-Resolution
Jiang, K., Yang, M., Xiao, Y., Wu, J., Wang, G., Feng, X., & Jiang, J. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3597745 · Cited by 44
“For real-world evaluation, perceptual quality is assessed with two no-reference metrics: natural image quality evaluator (NIQE) [65] and contrastive language–image pretraining for image quality assessment (CLIPIQA) [66].”
Towards Ultra-High-Definition Image Deraining: A Benchmark and an Efficient Method
Chen, H., Chen, X., Wu, C., Zheng, Z., Pan, J., & Fu, X. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3660153 · Cited by 44
A Prediction Backed Model for Quality Assessment of Screen Content and 3-D Synthesized Images
Jakhetiya, V., Gu, K., Lin, W., Li, Q., & Jaiswal, S. (2018) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2017.2756666 · Cited by 38
“human vision modeling [18] or some natural scene statistics models [19], [20].”
BackgroundNo Reference Image Quality Assessment based on Multi-Expert Convolutional Neural Networks
Fan, C., Zhang, Y., Feng, L., & Jiang, Q. (2018) · IEEE Access · doi:10.1109/access.2018.2802498 · Cited by 44
“To analyze the IQA performance over different distortion types more precisely, we compare the performance of some of state-of-the-art IQA schemes, including BRISQUE [18], BLIINDS-II [6], DIIVINE [19], [20], NSS-TS [21], CORNIA [13], TCLT-Gray [22], and NIQE [23].”
MethodHigh-resolution seismic tomography of Long Beach, CA using machine learning
Bianco, M. J., Gerstoft, P., Olsen, K. B., & Lin, F. (2019) · Scientific Reports · doi:10.1038/s41598-019-50381-z · Cited by 44
Extreme-Quality Computational Imaging via Degradation Framework
Chen, S., Feng, H., Gao, K., Xu, Z., & Chen, Y. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00263 · Cited by 44
“Moreover, we note that KPN and LP-KPN are designed to deal with spatially variant degradation, and they perform better in NIQE.”
MethodEnlightening Low-Light Images With Dynamic Guidance for Context Enrichment
Zhu, L., Yang, W., Chen, B., Lu, F., & Wang, S. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3146731 · Cited by 44
Peng, Y., Chen, Y.-R., Chen, Z., Wang, J.-H., & Huang, S.-C. (2022) · Sensors · doi:10.3390/s22062168 · Cited by 45
“Table 1 displays objective comparisons among the methods on the UIEB dataset [25] based on UCIQE [46] and NIQE [47], where the proposed method performs favorably against the other state-of-the-art approaches.”
MethodInfluentialMultiscale Attentive Image De-Raining Networks via Neural Architecture Search
Cai, L., Fu, Y., Huo, W., Xiang, Y., Zhu, T., Zhang, Y., Zeng, H., & Zeng, D. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3207516 · Cited by 44
“We observe that as we reduced the number of multi-scale attentive cells, the performances on PSNR, SSIM, and NIQE are consistently degraded.”
MethodInfluentialAn Underwater Image Quality Assessment Metric
Guo, P., Liu, H., Zeng, D., Xiang, T., Li, L., & Gu, K. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3187212 · Cited by 44
“2) Alternative IQA Metrics for Comparative Analysis: We compare our proposed UWEQM metric with 11 state-of-the-art IQA metrics including BRISQUE [35], NIQE [34], BLI-INDS II [47], SSEQ [48], LPC [49], UICM [50], UISM [50], UIConM [50], UIQM [50], UCIQE [40] and UEIQM [27].”
MethodPseudo-Supervised Low-Light Image Enhancement With Mutual Learning
Luo, Y., You, B., Yue, G., & Ling, J. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3284856 · Cited by 44
Personalized Generation In Large Model Era: A SurveyPreprint
Xu, Y., Zhang, J., Salemi, A., Hu, X., Wang, W., Feng, F., Zamani, H., He, X., & Chua, T. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.02614 · Cited by 45
Applicability of Existing Objective Metrics of Perceptual Quality for Adaptive Video Streaming
Søgaard, J., Krasula, L., Shahid, M., Temel, D., Brunnström, K., & Razaak, M. (2016) · Electronic Imaging · doi:10.2352/issn.2470-1173.2016.13.iqsp-206 · Cited by 43
“• Naturalness Image Quality Evaluator (NIQE) features [19].”
BackgroundImage data assessment approach for deep learning-based metal surface defect-detection systems
Lin, H.-I., & Wibowo, F. S. (2021) · IEEE Access · doi:10.1109/access.2021.3068256 · Cited by 43
“NIQE [31] computes the 36 identical natural scene statistic (NSS) features from the patches of the image, fits them with a multivariate Gaussian (MVG) model, and compares its MVG to the natural MVG model.”
BackgroundMethodReal-World Non-Homogeneous Haze Removal by Sliding Self-Attention Wavelet Network
Feng, Y., Meng, X., Zhou, F., Lin, W., & Su, Z. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3256414 · Cited by 43
“The NIQE [52] value and R score [53] value of the proposed method are 2.8775 and 1.9857, respectively.”
MethodInfluentialLearning Temporal-Ordered Representation for Spike Streams Based on Discrete Wavelet Transforms
Zhang, J., Jia, S., Yu, Z., & Huang, T. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i1.25085 · Cited by 43
“We use three metrics to assess the image quality: NIQE(Mittal, Soundararajan, and Bovik 2013), BRISQUE(Mittal, Moorthy, and Bovik 2012), and 2D entropy(Xi, Guosui, and Ni 1999).”
MethodExploring a radically new exponential Retinex model for multi-task environments
Rahman, Z.-U., Bhutto, J. A., Aamir, M., Dayo, Z. A., & Guan, Y. (2023) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2023.101635 · Cited by 43
“Similarly, a lower value of PIQE, BTMQI, DI, NIQE, LOE, VGG16-PFS, SSEQ, IP-NIQE and LPIPS indicates that visual quality has less color distortion and better perceptual effect.”
Influential3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation
Zhang, S., Zhang, Y., Zheng, Q., Ma, R., Hua, W., Bao, H., Xu, W., & Zou, C. (2024) · 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/cvpr52733.2024.00969 · Cited by 43
“We evaluate the quality of our generated images using CLIP Score (CS), Inception Score (IS), Blind/Referenceless Image Spatial Quality Evalua-tor (BRISQUE) [36] and Natural Image Quality Evaluator (NQIE) [37].”
MethodBlind image quality assessment with improved natural scene statistics model
Zhang, Y., Wu, J., Xie, X., Li, L., & Shi, G. (2016) · Digital Signal Processing · doi:10.1016/j.dsp.2016.05.012 · Cited by 43
“Three popular NR metrics are selected for performance comparison, which are BIQI [46], DIIVINE and NIQE.”
MethodInfluentialPerceptual Adaptation of Image Based on Chevreul–Mach Bands Visual Phenomenon
Khosravy, M., Gupta, N., Marina, N., Sethi, I. K., & Asharif, M. R. (2017) · IEEE Signal Processing Letters · doi:10.1109/lsp.2017.2679608 · Cited by 43
Contrast enhancement of low-light image using histogram equalization and illumination adjustment
Banik, P. P., Saha, R., & Kim, K. (2018) · International Conference on Electronics, Information, and Communication (ICEIC) · doi:10.23919/elinfocom.2018.8330564 · Cited by 43
“We also measure the quality of image with our method and HE method by naturalness image quality evaluator (NIQE) [6] and colorfulness-based patch-based contrast quality index (CPCQI) [7] nonreference image quality assessment metric and we list the quality value of these two methods in Table 1.”
MethodA New Local Fractional Entropy-Based Model for Kidney MRI Image Enhancement
Al-Shamasneh, A. R., Jalab, H. A., Shivakumara, P., Obaidellah, U. H. B., Ibrahim, R. W., & El-Melegy, M. (2018) · Entropy · doi:10.3390/e20050344 · Cited by 43
“Since the dataset is new, creating ground truth is not an easy task; therefore, we prefer to use standard, no-reference measures that do not require ground truth images, namely, BRISQUE [25] and NIQE [26].”
MethodDeep Blind Video Quality Assessment Based on Temporal Human Perception
Ahn, S., & Lee, S. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451450 · Cited by 43
“Taking averages is often used to analyze representative characteristics of global quality in QA problems [8], and standard deviation was used to analyze the global variation of local quality [12].”
MethodStudy of Subjective Quality and Objective Blind Quality Prediction of Stereoscopic Videos
Appina, B., Dendi, S. V. R., Manasa, K., Channappayya, S. S., & Bovik, A. C. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2914950 · Cited by 43
“As in NIQE [58], the pristine S3D video parameter sets ( f α p , f β p and f p ) are modeled using a Multivariate Gaussian (MVG) distribution denoted by N (ν, ), where ν and are the mean vector and covariance matrix respectively.”
MethodInfluentialSelf-citationPoster: MobiSR -- Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors
Lee, R., Venieris, S. I., Dudziak, Ł., Bhattacharya, S., & Lane, N. D. (2019) · ACM Annual International Conference on Mobile Computing and Networking (MobiCom) · doi:10.1145/3300061.3343410 · Cited by 43
Single image dehazing via self-constructing image fusion
Gao, Y., Su, Y., Li, Q., Li, H., & Li, J. (2019) · Signal Processing · doi:10.1016/j.sigpro.2019.107284 · Cited by 43
Cross-Reference Stitching Quality Assessment for 360° Omnidirectional Images
Li, J., Yu, K., Zhao, Y., Zhang, Y., & Xu, L. (2019) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3343031.3350973 · Cited by 43
“Our proposed method is sensitive to the local distortions and global color difference, while NIQE [21] and PIQE [23] (view in orange) do not generate favorable results tomatch the visual experience.”
MethodInfluentialBurdziakowski, P. (2020) · Remote Sensing · doi:10.3390/rs12050810 · Cited by 43
Zadtootaghaj, S., Schmidt, S., Sabet, S. S., Möller, S., & Griwodz, C. (2020) · ACM Multimedia Systems Conference (MMSys) · doi:10.1145/3339825.3391872 · Cited by 43
“Natural Image Quality Evaluator (NIQE), which is based on a space domain NSS model, is a learning-based quality estimation metric [16].”
BackgroundSuper Resolve Dynamic Scene from Continuous Spike Streams
Zhao, J. H., Xie, J., Xiong, R., Zhang, J., Yu, Z., & Huang, T. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00253 · Cited by 43
No-Reference Light Field Image Quality Assessment Using Four-Dimensional Sparse Transform
Xiang, J., Jiang, G., Yu, M., Jiang, Z., & Ho, Y. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3127398 · Cited by 43
“The performance of the proposed method is compared with that of several well-known NR 2DIQA methods (BRISQUE[15], GWH-GLBP[16](referred to as GLBP), and NIQE[47]), NR 3DIQA (SINQ[48]), NR multi-view IQA (MNSS[49], and Wang’s method[50]), FR LFIQA methods (MDFM [17], and Min’s method [18]), and NR LFIQA methods (BELIF…”
MethodSun, L. C., Bhatt, N. P., Liu, J. C., Fan, Z., Wang, Z., Humphreys, T. E., & Topcu, U. (2024) · 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802389 · Cited by 34
“To prevent outlier noisy images from being selected, the Naturalness Image Quality Evaluator (NIQE) metric [1] is used to select the highest quality frame across a sliding window.”
AIGCOIQA2024: Perceptual Quality Assessment of AI Generated Omnidirectional Images
Yang, L., Duan, H., Teng, L., Zhu, Y., Liu, X., Hu, M., Min, X., Zhai, G., & Callet, P. L. (2024) · arXiv · doi:10.48550/arxiv.2404.01024 · Cited by 27
“The selected models can be categorized into three groups: • Handcrafted-based models, which include QAC [27], BMPRI [28], NIQE [29], ILNIQE [30], HOSA [31], Table 1 .”
Background
Metadata
- Authors
- Mittal, A., Soundararajan, R., & Bovik, A. C.
- Affiliations
- The University of Texas at Austin (US)
- Venue
- IEEE Signal Processing Letters
- Published
- 2013-03
- Volume
- 20
- Issue
- 3
- Pages
- 209-212
- ISSN
- 1070-9908 (ISSN-L)
- 1558-2361
- OpenAlex
- W2102166818
- Cited by
- 6,766
- References
- 19
- Citations by year
- 2026: 856 · 2025: 1104 · 2024: 1023 · 2023: 860 · 2022: 757 · 2021: 598 · 2020: 463 · 2019: 329 · 2018: 241 · 2017: 182 · 2016: 129 · 2015: 98 · 2014: 92 · 2013: 31
- FWCI
- 73.09
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Signal Processing Letters (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, natural scene statistics, statistical features, natural image statistics, quality-aware features, image distortion
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.
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.