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 401–500 of 1,013
Effective Guided Image Filtering for Contrast Enhancement
Lu, Z., Long, B., Kang Li, B., & Fajin, L. (2018) · IEEE Signal Processing Letters · doi:10.1109/lsp.2018.2867896 · Cited by 97
“The naturalness image quality evaluator (NIQE) is utilized to evaluate image quality blindly [22].”
MethodSpatial–Frequency Dual-Domain Feature Fusion Network for Low-Light Remote Sensing Image Enhancement
Yao, Z., Fan, G., Fan, J., Gan, M., & Chen, C. L. P. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3434416 · Cited by 98
“For no-reference images, we assess their naturalness using the NIQE [14] metric.”
MethodA Probabilistic Quality Representation Approach to Deep Blind Image Quality PredictionPreprint
Zeng, H., Zhang, L., & Bovik, A. C. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.08190 · Cited by 97
“…split of training and testing sets will affect prediction accuracy, for a fair comparison, we re-ran the source codes of the DIIVINE [8], CORNIA [9], BRISQUE [10], NIQE [46], IL-NIQE [47], HOSA [19] and FRIQUEE-ALL [14] models using the same training and testing splits as we used for the PQR model.”
MethodSelf-citationQuality-Aware Image-Text Alignment for Opinion-Unaware Image Quality AssessmentPreprint
Agnolucci, L., Galteri, L., & Bertini, M. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2403.11176 · Cited by 100
“No-Reference Image Quality Assessment Due to its wide range of applications in real-world scenarios, in recent years research on NR-IQA has gained significant momentum [1, 3, 26, 29, 42].”
InfluentialSurvey on rain removal from videos or a single image
Wang, H., Wu, Y., Li, M., Zhao, Q., & Meng, D. (2021) · Science China Information Sciences · doi:10.1007/s11432-020-3225-9 · Cited by 97
Ultra-dense GAN for satellite imagery super-resolution
Wang, Z., Jiang, K., Yi, P., Han, Z., & He, Z. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.03.106 · Cited by 96
Blind quality assessment for image superresolution using deep two-stream convolutional networks
Zhou, W., Jiang, Q., Wang, Y., Chen, Z., & Li, W. (2020) · Information Sciences · doi:10.1016/j.ins.2020.04.030 · Cited by 96
“Due to the existence of original distortion-free HR images in the SR quality database [17], we compare our method with both the FR-IQA (i.e., PSNR, SSIM [33], multiscale SSIM denoted by MS-SSIM [35]) and NR-IQA algorithms, which include the blind/referenceless image spatial quality evaluator (BRISQUE) [18], natural im…”
BackgroundMethodInfluentialImage Defogging Quality Assessment: Real-World Database and Method
Liu, W., Zhou, F., Lü, T., Duan, J., & Qiu, G. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3033402 · Cited by 96
“To give a few examples, the performance for PSNR and NIQE [33] is rather poor.”
BackgroundMethodA survey on 360-degree video: Coding, quality of experience and streaming
Chiariotti, F. (2021) · Computer Communications · doi:10.1016/j.comcom.2021.06.029 · Cited by 97
Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models
Granot, N., Feinstein, B., Shocher, A., Bagon, S., & Irani, M. (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/cvpr52688.2022.01310 · Cited by 98
Trends and Prospects of Techniques for Haze Removal From Degraded Images: A Survey
Sahu, G., Seal, A., Bhattacharjee, D., Nasipuri, M., Brída, P., & Krejcar, O. (2022) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2022.3173443 · Cited by 96
U²PNet: An Unsupervised Underwater Image-Restoration Network Using Polarization
Shen, L., Xia, H., Zhang, X., Zhao, Y., Li, N., Kong, S. G., Wang, B., & Li, Z. (2024) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2024.3365693 · Cited by 96
“Quantitative Comparisons: For grayscale images, we can only compare natural image quality evaluator (NIQE) [91], average gradient (AG) [92] and edge intensity (EI) [93] metrics.”
BackgroundFusion of Heterogeneous Adversarial Networks for Single Image Dehazing
Park, J., Han, D. K., & Ko, H. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2975986 · Cited by 94
“We use PSNR and SSIM as full-reference image quality assessment (FR-IQA) metrics while BRISQUE [47] and NIQE [48] are leveraged as no-reference image quality assessment (NR-IQA) metrics.”
MethodTowards Low Light Enhancement With RAW Images
Huang, H., Yang, W., Hu, Y., Liu, J., & Duan, L. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3140610 · Cited by 95
“…BPDHE [5], LLNet [9], SICE [37], KinD [10], DeepUPE [38] and Zero-DCE [41], and RAW-based methods including EEMEFN [15] and ELD [14] on SID-Sony dataset and provide systematic benchmark results using various metrics including PSNR, SSIM [53], VIF [54], NIQE [55] and LPIPS [56], shown in Table VIII.”
UIEDP: Boosting underwater image enhancement with diffusion prior
Du, D., Li, E., Si, L., Zhai, W., Xu, F., Niu, J., & Sun, F. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125271 · Cited by 96
Beyond Human Opinion Scores: Blind Image Quality Assessment Based on Synthetic Scores
Ye, P., Kumar, J., & 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.2014.540 · Cited by 96
“Extensive experiments on standard IQA datasets show that BLISS significantly outperforms previous OF-BIQA methods and is comparable to state-of-the-art OA-BIQA methods.”
MethodText2NeRF: Text-Driven 3D Scene Generation With Neural Radiance Fields
Zhang, J., Li, X., Wan, Z., Wang, C., & Liao, J. (2024) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3361502 · Cited by 94
“Instead, we use two metrics, blind/referenceless image spatial quality evaluator (BRISQUE) [46] and natural image quality evaluator (NIQE) [47], on no-reference image quality assessment to evaluate rendering quality of generated 3D scenes.”
MethodSun, W., Gu, K., Ma, S., Zhu, W., Liu, N., & Zhai, G. (2018) · 2018 IEEE 20th International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2018.8547102 · Cited by 78
“Five general-purpose NR IQA metrics are compared in this paper, which are Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) [24], Natural Image Quality Evaluator (NIQE) [25], Gradient Magnitude and Laplacian Features (GMLF) [26], Quality-Aware Clusting (QAC) [27] and Six-step Blind Metric (SISBLIM) [28], r…”
MethodMobiSR: 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:10.1145/3300061.3345455 · Cited by 94
“ss functions, including perceptual [27] and adversarial losses [10]. These models focus on the perceptual quality of the image andareevaluatedonno-referencemetricssuchasNaturalImage Quality Evaluator [41] and perceptual score [38]. In this work, we focus on the former, i.e. mapping low-resolution images closer to thei…”
BackgroundYang, K.-F., Cheng, C., Zhao, S., Yan, H.-M., Zhang, X.-S., & Li, Y.-J. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-022-01745-y · Cited by 94
“Only the NIQE (Mittal et al., 2012)was usedon these datasets because there are nogroundtruth images provided for these datasets for full-reference quality metrics.”
BackgroundMethodInfluentialZhou, J., Gai, Q., Zhang, D., Lam, K., Zhang, W., & Fu, X. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3346384 · Cited by 94
“In this work, we employ the underwater image quality measure (UIQM) [54], underwater color image quality evaluation (UCIQE) [55], and natural image quality evaluator (NIQE) [56] as our NR metrics.”
MethodPolarization-Driven Solution for Mitigating Scattering and Uneven Illumination in Underwater Imagery
Shen, L., Reda, M., Zhang, X., Zhao, Y., & Kong, S. G. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3358828 · Cited by 94
“Additionally, we applied blind image quality evaluation models based on natural scene statistics, including Natural Image Quality Evaluator (NIQE) [65] and Integrated Local NIQE (ILNIQE) [66], as well as Average Gradient (AG) [67] and Edge Intensity (EI) [68], which characterize the degree of local…”
MethodGroup Maximum Differentiation Competition: Model Comparison with Few Samples
Ma, K., Duanmu, Z., Wang, Z., Wu, Q., Liu, W., Yong, H., Li, H., & Zhang, L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2889948 · Cited by 94
“The database focuses on the four aforementioned distortion types because many stateof-the-art IQA models declare themselves for successfully handling them [28], [29], [30], [31], [32] on small-scale IQA databases.”
BackgroundMethodLearning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment
Zheng, H., Yang, H., Fu, J., Zha, Z.-J., & Luo, J. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01008 · Cited by 94
PM₂.₅ Monitoring: Use Information Abundance Measurement and Wide and Deep Learning
Gu, K., Liu, H., Xia, Z., Qiao, J., Lin, W., & Thalmann, D. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3105394 · Cited by 93
Multi-Branch and Progressive Network for Low-Light Image Enhancement
Zhang, K., Yuan, C. Q., Li, J., Gao, X., & Li, M. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3266171 · Cited by 93
“Four non-reference quality evaluation indicators NIQE [39], BRISQUE [40], NIMA [41], and PaQ-2-PiQ [42] are used to evaluate the enhanced results of different methods, including MBLLEN [11], DeepLPF [24], MIRNet [26], SGM-Net [9], LLFlow [25], KinD ++ [28], and Bread [27].”
BackgroundMethodEvaluating Point Cloud From Moving Camera Videos: A No-Reference Metric
Zhang, Z., Sun, W., Zhu, Y., Min, X., Wu, W., Chen, Y., & Zhai, G. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3340894 · Cited by 93
“The NR projection-based meth-ods include BRISQUE [55], NIQE [52], PQA-net [32], VIIDEO [44],V-BLIINDS [45], TLVQM [46], VIDE-VAL [47], VSFA [48], RAPIQUE [49], StairVQA [50], BVQA [33], SimpVQA [34].”
Gan-based data augmentation to improve breast ultrasound and mammography mass classification
Jiménez-Gaona, Y., Carrión-Figueroa, D., Lakshminarayanan, V., & Rodríguez-Álvarez, M. J. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106255 · Cited by 93
Exploiting Diffusion Prior for Real-World Image Dehazing with Unpaired Training
Lan, Y., Cui, Z., Liu, C., Peng, J., Wang, N., Luo, X., & Liu, D. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i4.32469 · Cited by 93
“In cases where ground truth is unavailable, we evaluate them by no-reference metrics, including FID (Heusel et al. 2017), CLIPIQA (Wang, Chan, and Loy 2023), NIQE (Mittal, Soundararajan, and Bovik 2012), and MUSIQ (Ke et al. 2021).”
FineVQ: Fine-Grained User Generated Content Video Quality Assessment
Duan, H., Hu, Q., Wang, J., Yang, L., Xu, Z., Lü, L., Min, X., Cai, C., Ye, T., Zhang, X., et al. (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/cvpr52734.2025.00305 · Cited by 93
“…benchmark methods in our FineVD, which can be categories into three groups: (1) traditional image quality assessment (IQA) methods, including NIQE [39], QAC [69], HOSA [68]; (2) traditional video quality assessment (VQA) methods, including TLVQM [22], VIDEVAL [53], RAPIQUE [54]; (3) DNN-based VQA…”
Ding, G., Liu, Y., Zhang, R., & Xin, H. L. (2019) · Scientific Reports · doi:10.1038/s41598-019-49267-x · Cited by 95
Single image dehazing using a new color channel
Sahu, G., Seal, A., Krejcar, O., & Yazidi, A. (2020) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2020.103008 · Cited by 92
Zhou, X., Qiu, S., Joshi, P. S., Xue, C., Killiany, R., Mian, A. Z., Chin, S., Au, R., Kolachalama, V. B., & Initiative, F. T. A. D. N. (2021) · Alzheimer s Research & Therapy · doi:10.1186/s13195-021-00797-5 · Cited by 92
Perceptual Quality Assessment of Low-light Image Enhancement
Zhai, G., Sun, W., Min, X., & Zhou, J. (2021) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3457905 · Cited by 92
“In the previous studies of low-light image enhancement, some FR IQA measures such as PSNR, SSIM, GMSD, FSIM, or some NR IQA measures such as NIQE [49], NFERM [17] are frequently used to evaluate the enhancement effect.”
MethodInfluentialGenerative Steganography Network
Ping, W., Li, S., Zhang, X., Luo, G., Qian, Z., & Zhou, Q. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3548217 · Cited by 92
“Results show our stego images are more natural with a lower Niqe score and a higher payload, in which a non-reference image assessor Niqe[22] is used to evaluate the image quality.”
Yuan, Z., Zeng, J., Wei, Z., Jin, L., Zhao, S., Liu, X., Zhang, Y., & Zhou, G. (2023) · IEEE Transactions on Power Delivery · doi:10.1109/tpwrd.2023.3269206 · Cited by 92
“For objective study of the image quality comparison, we conduct quantitative assessment of the resulting images using NaturalImageQualityEvaluator(NIQE)metric[18]withresults showninTableI,whereACL-CLAHEshowsobviousimprove-mentoverexistingschemes.”
MethodWu, H., Zhang, E., Liao, L., Chen, C., Hou, J., Wang, A., Sun, W., Yan, Q., & Lin, W. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3611737 · Cited by 92
“Dimensions (in codes) A-1 A-2 A-3 A-4 [A-5] A-all T-1 T-2 T-3 T-4 [T-5] T-6 T-7 [T-8] T-all O Methods PLCC PLCC PLCC PLCC PLCC PLCC PLCC PLCC PLCC PLCC PLCC PLCC PLCC PLCC PLCC PLCC Zero-shot Methods: (not fine-tuned on any dimensions) (c, spatial) NIQE [33] 0.”
MethodZhang, Z., Wu, H., Zhang, E., Zhai, G., & Lin, W. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3445770 · Cited by 92
Enhancing Descriptive Image Quality Assessment With a Large-Scale Multi-Modal Dataset
You, Z., Gu, J., Cai, X., Li, Z., Zhu, K., Dong, C., & Xue, T. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3639998 · Cited by 92
“Initially, human-designed natural image statistics are adopted [24], [25], [26], [27], [28], [29], [30].”
Tu, J., Mei, G., Ma, Z., & Piccialli, F. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3190322 · Cited by 91
Nair, N. G., Mei, K., & Patel, V. M. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00343 · Cited by 91
QCNN-H: Single-Image Dehazing Using Quaternion Neural Networks
Frants, V., Agaian, S. С., & Panetta, K. A. (2023) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2023.3238640 · Cited by 91
“For quantitative evaluation, full-reference image quality metrics SSIM and PSNR [57] on Y-channel in CbCrY color-space, NIQE [58] were used to quantify the naturalness of the dehazed image, where the lower score indicated better visual performance, and the visibility index (VI) and realness index…”
MethodData-Driven single image deraining: A Comprehensive review and new perspectives
Zhang, Z., Wei, Y., Zhang, H., Yang, Y., Yan, S., & Wang, M. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.109740 · Cited by 92
PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image RestorationPreprint
Gu, J., Cai, H., Chen, H., Ye, X., Ren, J., & Dong, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.12142 · Cited by 91
Blind Image Quality Assessment with a Probabilistic Quality Representation
Zeng, H., Zhang, L., & Bovik, A. C. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451285 · Cited by 90
“Since the split of training and testing sets will affect prediction accuracy, for fair comparison, we re-ran the source codes of the DIIVINE [1], CORNIA [2], BRISQUE [3], NIQE [22], HOSA [8] and FRIQUEE-ALL [5] using the same training and testing splits as we used for the PQR model.”
MethodSelf-citationGu, K., Qiao, J., Lee, S., Liu, H., Lin, W., & Callet, P. L. (2019) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2019.2906768 · Cited by 90
“Experiments demonstrate that many IQA models, regardless of whether they are full reference (FR) [22]–[25] or no reference (NR) [26]–[29], cannot yield reliable quality scores when assessing DIBR-synthesized views.”
BackgroundMethodBetter Than Reference in Low-Light Image Enhancement: Conditional Re-Enhancement Network
Zhang, Y., Di, X., Zhang, B., Ji, R., & Wang, C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3135473 · Cited by 90
MSAFF-Net: Multiscale Attention Feature Fusion Networks for Single Image Dehazing and Beyond
Lin, C., Rong, X., & Yu, X. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3155937 · Cited by 90
“…to objectively quantify the With the exception of the artificial evaluation of image quality, there is a more commonly used objective evaluation index called the natural image quality evaluator (NIQE) [49], which can quantify the quality of an image when a ground truth image is unavailable.”
MethodSelf-Supervised Low-Light Image Enhancement Using Discrepant Untrained Network Priors
Liang, J., Xu, Y., Quan, Y., Shi, B., & Ji, H. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3181781 · Cited by 90
“However, it results in a high NIQE, which can be improved by the proposed IGD module.”
MethodInfluentialDeep learning in medical image super resolution: a review
Yang, H., Wang, Z., Liu, X., Li, C., Xin, J., & Wang, Z. (2023) · Applied Intelligence · doi:10.1007/s10489-023-04566-9 · Cited by 90
“NIQE: Natural image quality evaluator (NIQE) [128] is a popular IQA index without reference.”
BackgroundACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-Resolution
Niu, A., Pham, T. X., Zhang, K., Sun, J., Zhu, Y., Yan, Q., Kweon, I. S., & Zhang, Y. (2024) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2024.3374122 · Cited by 90
“Since our work focuses on the perceptual quality, except the distortion metrics: PSNR and SSIM, we also provide perceptual metrics: LPIPS [68] and NIQE [69] to show that our method can generate better perceptual results than other methods.”
MethodDMFourLLIE: Dual-Stage and Multi-Branch Fourier Network for Low-Light Image Enhancement
Zhang, T., Liu, P., Zhao, M., & Lv, H. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681083 · Cited by 90
“We measure the no-reference Natural Image Quality Eval-uator (NIQE [28]) scores on five non-paired datasets.”
MethodNo-Reference Image Quality Assessment by Wide-Perceptual-Domain Scorer Ensemble Method
Liu, T.-J., & Liu, K.-H. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2771422 · Cited by 90
“DIIVINE [14], BLIINDS-II [15], BRISQUE [16], NIQE [19], and DLIQA [20].”
MethodInfluentialSubjective and Objective De-Raining Quality Assessment Towards Authentic Rain Image
Wu, Q., Wang, L., Ngan, K. N., Li, H., Meng, F., & Xu, L. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.2972566 · Cited by 89
“, NIQE [59], ILNIQE [60], QAC [61], and LPSI [62]).”
MethodInfluentialSubjective and Objective Quality Assessment of High Frame Rate Videos
Madhusudana, P. C., Yu, X., Birkbeck, N., Wang, Y., Adsumilli, B., & Bovik, A. C. (2021) · IEEE Access · doi:10.1109/access.2021.3100462 · Cited by 65
“When computing NIQE, scores were obtained on every frame, then averaged to obtain overall video scores.”
MethodSelf-citationMIRROR: Model Inversion for Deep Learning Network with High Fidelity
An, S., Tao, G., Xu, Q., Liu, Y., Shen, G., Yao, Y., Xu, J., & Zhang, X. (2022) · Network and Distributed System Security Symposium · doi:10.14722/ndss.2022.24335 · Cited by 90
“NIQE was proposed as a non-reference metric for the perceptual quality evaluation [43].”
MethodSimple low-light image enhancement based on Weber–Fechner law in logarithmic space
Wang, W., Chen, Z., & Yuan, X. (2022) · Signal Processing Image Communication · doi:10.1016/j.image.2022.116742 · Cited by 89
Ichi, E., & Dorafshan, S. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104523 · Cited by 89
Motion-Guided Latent Diffusion for Temporally Consistent Real-World Video Super-Resolution
Yang, X., He, C., Ma, J., & Zhang, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72784-9_13 · Cited by 89
Towards Unified Deep Image Deraining: A Survey and a New Benchmark
Chen, X., Pan, J., Dong, J., & Tang, J. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3556133 · Cited by 90
“…truth images, the non-reference IQA indicators are used to quantitatively evaluate the restoration performance, including Natural Image Quality Evaluator (NIQE) [116], Blind/Referenceless Image Spatial Quality Eval-uator (BRISQUE) [117], and Spatial-Spectral Entropy-based Quality (SSEQ) [118].”
A Comprehensive Survey on Underwater Image Enhancement Based on Deep Learning
Cong, X., Zhao, Y., Gui, J., Hou, J., & Tao, D. (2026) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2026.3668671 · Cited by 89
“The reward function consists of three no-reference metrics that evaluate underwater image quality from different perspectives, which is (13) where a , b and c represent the metric UCIQE [160], NIQE [105] and URanker [38], respectively.”
Kuang, H., Zhang, X., Li, Y.-J., Chan, L. L. H., & Yan, H. (2017) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2016.2598192 · Cited by 84
“We also utilized two commonly used noreference (NR) IQA metrics: Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) [43] that quantifies possible losses of “naturalness” and Naturalness Image Quality Evaluator (NIQE) [44] that analyze measurable deviations from statistical regularities observed in natural i…”
MethodPawar, K., Chen, Z., Shah, N. J., & Egan, G. F. (2019) · NMR in Biomedicine · doi:10.1002/nbm.4225 · Cited by 88
Sun, W., Wang, T., Min, X., Yi, F., & Zhai, G. (2021) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew53276.2021.9455999 · Cited by 88
LAE-Net: A locally-adaptive embedding network for low-light image enhancement
Liu, X., Ma, W., Ma, X., & Wang, J. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.109039 · Cited by 88
Bringing Old Films Back to Life
Wan, Z., Zhang, B., Chen, D., & Liao, J. (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/cvpr52688.2022.01717 · Cited by 88
Multi-weather Image Restoration via Domain Translation
Patil, P. W., Gupta, S., Rana, S., Venkatesh, S., & Murala, S. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01983 · Cited by 88
“Average Naturalness Image Quality Evaluator (NIQE) [21], Entropy and Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) [20] evaluation metrics are used in case of real-world weather degraded image restoration.”
Blind Deep S3D Image Quality Evaluation via Local to Global Feature Aggregation
Oh, H., Ahn, S., Kim, J., & Lee, S. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2725584 · Cited by 87
DroneSURF: Benchmark Dataset for Drone-based Face Recognition
Kalra, I., Singh, M., Nagpal, S., Singh, R., Vatsa, M., & Sujit, P. B. (2019) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg.2019.8756593 · Cited by 87
“On the other hand, intelligent frame selection, based on the quality (NIQE) results in an improved rank-1 performance.”
MethodNTIRE 2022 Challenge on Perceptual Image Quality Assessment
Gu, J., Cai, H., Dong, C., Ren, J., Timofte, R., Gong, Y., Lao, S., Shi, S., Wang, J., Yang, S., et al. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00109 · Cited by 87
EFINet: Restoration for Low-Light Images via Enhancement-Fusion Iterative Network
Liu, C., Wu, F., & Wang, X. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3195996 · Cited by 87
“We quantitatively evaluate the performances of all the methods with four commonly used metrics, i.e., NIQE [54], Angle Error (AE), PSNR and SSIM [50].”
MethodUIE-Convformer: Underwater Image Enhancement Based on Convolution and Feature Fusion Transformer
Wang, B., Xu, H., Jiang, G., Yu, M., Ren, T., Luo, T., & Zhu, Z. (2024) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2024.3359061 · Cited by 87
“For the SQUID dataset, no-reference evaluation metrics UCIQE [59], UIQM [60], NIQE [61] are used to evaluate the enhanced performance of different methods.”
MethodPGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidance
Yang, P., Zhou, S., Tao, Q., & Loy, C. C. (2023) · neural information processing systems · doi:10.52202/075280-1398 · Cited by 87
A feature-based approach for image tampering detection and localization
Verdoliva, L., Cozzolino, D., & Poggi, G. (2014) · 2014 IEEE International Workshop on Information Forensics and Security (WIFS) · doi:10.1109/wifs.2014.7084319 · Cited by 77
“In the following we describe how features are extracted, and how they are used for detection and localization.”
MethodA fusion-based method for single backlit image enhancement
Wang, Q.-H., Fu, X., Zhang, X.-P. S., & Ding, X. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7533126 · Cited by 86
“ASSESSMENT RESULTS OF NIQE [15].”
MethodPhoto-Realistic Image Super-Resolution via Variational Autoencoders
Liu, Z.-S., Siu, W.-C., & Chan, Y. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3003832 · Cited by 86
“This measurement approach combines the no-reference image quality measures of Ma et al. [36] and NIQE [29] as Note that the lower PI we get, the better perceptual quality we can obtain.”
BackgroundMethodDegrade Is Upgrade: Learning Degradation for Low-Light Image Enhancement
Jiang, K., Wang, Z., Wang, Z., Chen, C., Yi, P., Lü, T., & Lin, C. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i1.19992 · Cited by 87
Semi-Supervised Image Deraining Using Knowledge Distillation
Cui, X., Wang, C., Ren, D., Chen, Y., & Zhu, P. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3190516 · Cited by 86
“Given that real datasets have no ground truths, we adopt NIQE [50] as an evaluation metric.”
MethodSelfPromer: Self-Prompt Dehazing Transformers with Depth-Consistency
Wang, C., Pan, J., Lin, W., Dong, J., Wang, W. W., & Wu, X.-M. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i6.28340 · Cited by 86
CWNet: Causal Wavelet Network for Low-Light Image Enhancement
Zhang, T., Liu, P., Lu, Y., Cai, M., Zhang, Z., Zhang, Z., & Zhou, Q. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00822 · Cited by 87
“The evaluation was conducted using the no-reference image quality assessment metric NIQE [28], with lower scores indicating better perceptual quality and naturalness.”
Generative AI for Autonomous Driving: Frontiers and Opportunities
Wang, Y., Xing, S., Cui, C., Li, R., Hua, H., Tian, K., Mo, Z., Gao, X., Pavone, M., Zhou, S., et al. (2026) · ACM Computing Surveys · doi:10.1145/3838726 · Cited by 86
“Traditional perceptual quality metrics [60, 85, 153, 210, 213, 238, 239, 283, 288, 289] that are typically used to evaluate user-generated videos [212, 213] often fail to fully capture how humans perceive this new type of content.”
Fundus image quality assessment: survey, challenges, and future scope
Raj, A., Tiwari, A. K., & Martini, M. G. (2019) · IET Image Processing · doi:10.1049/iet-ipr.2018.6212 · Cited by 86
Learning the Degradation Distribution for Blind Image Super-ResolutionPreprint
Luo, Z., Huang, Y., Li, S., Wang, L., & Tan, T. N. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.04962 · Cited by 86
Low-Light Image and Video Enhancement: A Comprehensive Survey and BeyondPreprint
Zheng, S., Ma, Y., Pan, J., Lu, C., & Gupta, G. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2212.10772 · Cited by 86
“Non-Reference Metrics Natural Image Quality Evaluator (NIQE) [69] and Lightness order Error (LOE) [13] are nonreference image quality evaluation metrics.”
BackgroundHuang, Z., Fang, H., Li, Q., Li, Z., Zhang, T., Sang, N., & Li, Y. (2018) · Infrared Physics & Technology · doi:10.1016/j.infrared.2018.08.019 · Cited by 85
Fast Enhancement for Non-Uniform Illumination Images using Light-weight CNNs
Lv, F., Liu, B., & Lu, F. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413925 · Cited by 85
“Algorithm ↑PSNR ↑SSIM [40] ↑VIF [35] ↓LOE [43] ↓NIQE[32] Params Runtime”
Yang, J., Zhao, Y., Liu, J., Jiang, B., Meng, Q., Lu, W., & Gao, X. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.3024627 · Cited by 78
“…integrity evaluation (DIIVINE) [20], blind/referenceless image spatial quality evaluator (BRISQUE) [21], natural image quality eval-uator (NIQE) [22], the integrated-local NIQE (IL-NIQE) [23], blind image integrity notator using DCT statistics (BLIINDS-II) [24], and the quality-aware clustering…”
MethodDing, X., Wang, Y., Xu, Z., Welch, W. J., & Wang, Z. J. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3228915 · Cited by 87
“S.5.7 some example fake images from candidate models and line graphs of FID/NIQE/Diversity/Lable Score versus Age in Fig.”
BackgroundInfluentialGuo, S., & Gallego, G. (2024) · IEEE Transactions on Robotics · doi:10.1109/tro.2024.3378443 · Cited by 85
“15) by means of the naturalness image quality evaluator (NIQE) [59] and the perception-based image qualityevaluator(PIQE)[60]:thelowerthescores,thehigherthe imagequality.”
MethodBringing Textual Prompt to AI-Generated Image Quality Assessment
Qu, B., Li, H., & Gao, W. (2024) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme57554.2024.10688254 · Cited by 85
“In terms of perception, our method is compared with 12 perceptual quality methods, including handcrafted-based metrics CEIQ [16], NIQE [17], DSIQA [18], SISBLIM [19] support vector regression-based metrics GMLF [20], HIGRADE [21] and deep learning-based (DL) metrics DBCNN [5], CNNIQA [12], HyperNet…”
MethodMWFormer: Multi-Weather Image Restoration Using Degradation-Aware Transformers
Zhu, R., Tu, Z., Liu, J., Bovik, A. C., & Fan, Y. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3501855 · Cited by 85
“The quantitative comparisons using NIQE [58] are reported in Table IV, indicating that MWFormer outperforms the previous state-of-the-art models on this most widely adopted no-reference metric.”
Self-citationQuality Assessment for AI Generated Images With Instruction Tuning
Wang, J., Duan, H., Zhai, G., & Min, X. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3651009 · Cited by 86
“Based on different feature extraction and evaluation meth-ods, current popular models for image quality assessment can be classified into three categories: (1) Handcrafted-based models, including: NIQE [60], BRISQUE [61], QAC [62], BM-PRI [63], HOSA [64], BPRI [65], HIGRADE [66], etc.”
No-Reference Video Quality Assessment Based on Artifact Measurement and Statistical Analysis
Zhu, K., Li, C., Asari, V., & Saupe, D. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2363737 · Cited by 77
“The natural image quality evaluator in [23] uses a simple and successful spacial-domain natural scene statistic (NSS) model to construct a quality aware collection of statistical features.”
MethodRecurrent and Dynamic Models for Predicting Streaming Video Quality of Experience
Bampis, C. G., Li, Z., Katsavounidis, I., & Bovik, A. C. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2815842 · Cited by 84
“In D1, there is no rebuffering in the distorted videos and hence it is straightforward to study the performance between various leading VQA models: PSNR, NIQE [35], VMAF (version 0.”
MethodSelf-citationUIQI: A Comprehensive Quality Evaluation Index for Underwater Images
Liu, Y., Gu, K., Cao, J., Wang, S., Zhai, G., Dong, J., & Kwong, S. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3301226 · Cited by 84
“In [25], Mittal et al. fitted the NSS features with the multivariate Gaussian (MVG) model on a set of pristine images, which served as the side information to deduce the image quality score.”
MethodA Novel Blind Image Quality Assessment Method Based on Refined Natural Scene Statistics
Ou, F.-Z., Wang, Y., & Zhu, G. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803047 · Cited by 84
“In order to verify the effectiveness of the proposed method, five mainstream NSS-based NR-IQA methods including BLIINDS-II [4], BRISQUE [3], CORNIA [5], DIIVINE [2], NIQE [6] are used for comparison.”
BackgroundMethodCcGAN: Continuous Conditional Generative Adversarial Networks for Image GenerationPreprint
Ding, X., Wang, Y., Xu, Z., Welch, W. J., & Wang, Z. J. (2020) · arXiv (Cornell University) · Cited by 83
Blind Quality Metric of DIBR-Synthesized Images in the Discrete Wavelet Transform Domain
Wang, G., Wang, Z., Gu, K., Li, L., Xia, Z., & Wu, L. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2945675 · Cited by 83
“The quality of distorted images is expressed as a simple distance measure between model statistics and those distorted images.[18].”
BackgroundStudy of 3D Virtual Reality Picture Quality
Chen, M., Jin, Y., Goodall, T., Yu, X., & Bovik, A. C. (2019) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2019.2956408 · Cited by 83
“NR-IQA models have also been proposed, including BRISQUE [19], NIQE [20], BLIINDS [21], and CORNIA [22].”
Self-citationYan, Y., Liu, C., Chen, C., Sun, X., Jin, L., Peng, X., & Zhou, X. S. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3065731 · Cited by 83
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.