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 601–700 of 1,013
Adaptive Near-Infrared and Visible Fusion for Fast Image Enhancement
Awad, M., Elliethy, A. S., & Aly, H. A. (2019) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2019.2956873 · Cited by 71
“To quantitatively compute how much a fusion approach degrades or enhances a VS image, we aggregate several blind (no-reference) image quality measures (BIQM) [28]–[33] in a novel way.”
BackgroundMethodInfluentialA trusted medical image super-resolution method based on feedback adaptive weighted dense network
Chen, L., Yang, X., Jeon, G., Anisetti, M., & Liu, K. (2020) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2020.101857 · Cited by 71
Multi-Scale Hybrid Fusion Network for Single Image Deraining
Jiang, K., Wang, Z., Yi, P., Chen, C., Wang, G., Han, Z., Jiang, J., & Xiong, Z. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3112235 · Cited by 70
“…as peak signal-to-noise ratio (PSNR), feature similarity (FSIM) [64], structural similarity (SSIM) [65], naturalness image quality evaluator (NIQE) [66], and spatial-spectral entropy-based quality (SSEQ) [67], as well as the mainstream vision-oriented tasks (image detection and segmentation) for…”
BackgroundWavelet-Based Texture Reformation Network for Image Super-Resolution
Li, Z., Kuang, Z.-S., Zhu, Z.-L., Wang, H.-P., & Shao, X.-L. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3160072 · Cited by 70
Yang, X., Wang, Z., Zhao, J., & Yang, D. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3165371 · Cited by 71
“Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM) and Frechet Inception Distance (FID) [37] are applied as subjective evaluation indicators, Natural Image Quality Evaluator (NIQE) [38] and Learned Perceptual Image Patch Similarity (LPIPS) [39] as objective evaluation indicators.”
MethodA review on Single Image Super Resolution techniques using generative adversarial network
Singla, K., Pandey, R., & Ghanekar, U. (2022) · Optik · doi:10.1016/j.ijleo.2022.169607 · Cited by 70
DAWN: Direction-aware Attention Wavelet Network for Image Deraining
Jiang, K., Liu, W., Wang, Z., Zhong, X., Jiang, J., & Lin, C. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3611697 · Cited by 70
“Quantitative results of NIQE [38] and SSEQ [31] are listed in Table 4, where smaller NIQE and SSEQ scores indicate better perceptual quality and clearer contents.”
BackgroundLarge Multi-modality Model Assisted AI-Generated Image Quality Assessment
Wang, P., Sun, W., Zhang, Z., Jia, J., Jiang, Y., Zhang, Z., Min, X., & Zhai, G. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681471 · Cited by 70
“For all datasets, we opt for handcrafted feature-based BRISQUE [26], NIQE [27] and IL-NIQE [56], DNN-based HyperIQA [41], MANIQA [51], MUSIQ [17], DBCNN [57], StairIQA [42], BAID [53], and LMM-based CLIP-IQA [44], CLIPIQA+ [44] and Q-Align [47].”
Watch Your Steps: Local Image and Scene Editing by Text Instructions
Mirzaei, A., Aumentado‐Armstrong, T., Brubaker, M. A., Kelly, J., Levinshtein, A., Derpanis, K. G., & Gilitschenski, I. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72920-1_7 · Cited by 70
Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text
Li, X., Lai, Z., Xu, L., Qu, Y., Cao, L., Zhang, S., Dai, B., & Ji, R. (2024) · neural information processing systems · doi:10.52202/079017-2391 · Cited by 71
Efficient No-Reference Quality Assessment and Classification Model for Contrast Distorted Images
Nafchi, H. Z., & Cheriet, M. (2018) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2018.2818402 · Cited by 70
“, RIQMC [21], QMC [23] and RCIQM [24], and four NR-IQAs including QAC [37], NIQE [12], NSS [25] and NIQMC [26] were used in the experiments.”
MethodLi, C., Tang, S., Kwan, H. K., Yan, J., & Zhou, T. (2020) · IEEE Access · doi:10.1109/access.2020.3019354 · Cited by 70
“To further assess the proposed method, we select Entropy, NIQE [52] and IL-NIQE [53], UIQM [54], UCIQE [55] to objectively evaluate the results of our method.”
BackgroundMethodA Real-World Benchmark for Sentinel-2 Multi-Image Super-Resolution
Kowaleczko, P., Tarasiewicz, T., Ziaja, M., Kostrzewa, D., Nalepa, J., Rokita, P. S., & Kawulok, M. (2023) · Scientific Data · doi:10.1038/s41597-023-02538-9 · Cited by 70
“Although some reference-free metrics, like natural image quality evaluator (NIQE) 31 , perception-based image quality evaluator (PIQE) 32 or no-reference quality metric (NRQM) 33 , are also exploited for scoring real-world SR 9,34 , they primarily assess the quality of a reconstructed image rather than accuracy of rec…”
Zhou, W., Yu, L., Qiu, W., Zhou, Y., & Wu, M. (2017) · Information Sciences · doi:10.1016/j.ins.2017.02.049 · Cited by 69
“Existing mainstream NR-IQA can be divided into two main categories: distortion-specific NR-IQA and general-purpose NR-IQA [13, 12].”
BackgroundUnderwater Image Quality Assessment: Subjective and Objective Methods
Guo, P., He, L., Liu, S., Zeng, D., & Liu, H. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3074825 · Cited by 69
“BRISQUE, NIQE, BLIIND-II metrics were mainly devised to assess artifacts in image compression and transmission, 7 (a) (b) (c) (d) (e) 0 2 4 6 8 10 12 UEIQM 0 2 4 6 8 10 12 M O S (f) Fig.”
BackgroundInfluentialA Generalized Physical-knowledge-guided Dynamic Model for Underwater Image Enhancement
Mu, P., Xu, H., Liu, Z., Wang, Z., Chan, S., & Bai, C. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3612323 · Cited by 69
“We also adopt Natural Image Quality Evaluator (NIQE [41]), which evaluates the naturalness of generated images.”
MethodUnderwater Optical Imaging: Methods, Applications and Perspectives
Hao, Y., Yuan, Y., Zhang, H., & Zhang, Z. (2024) · Remote Sensing · doi:10.3390/rs16203773 · Cited by 69
Emulating Self-attention with Convolution for Efficient Image Super-Resolution
Lee, D., Yun, S., & Ro, Y. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02268 · Cited by 69
Tasking on Natural Statistics of Infrared Images
Goodall, T., Bovik, A. C., & Paulter, N. G. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2496289 · Cited by 69
“Kaser [19] and Goodall and Bovik [20] modeled the fit of the BRISQUE [21] and NIQE [22] image quality models to LWIR images showing that these visible light models fit reasonably well to LWIR image data.”
BackgroundSelf-citationFast Scale-Adaptive Bilateral Texture Smoothing
Ghosh, S., Gavaskar, R. G., Panda, D., & Chaudhury, K. N. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2916589 · Cited by 69
“The edge count for each color channel is mentioned in the caption. evaluate the performance, we use the no-reference quality metric NIQE [54].”
MethodLearning To Blindly Assess Image Quality In The Laboratory And Wild
Zhang, W., Ma, K., Zhai, G., & Yang, X. (2020) · 2020 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip40778.2020.9191278 · Cited by 55
“Although NIQE [12] and its feature-enriched version ILNIQE [13] are designed for arbitrary distortion types, they do not perform well on realistic distortions and challenging synthetic distortions in TID2013 [7].”
MethodInfluentialSubjective and Objective Quality Assessment of High Frame Rate Videos
Madhusudana, P. C., Yu, X., Birkbeck, N., Wang, Y., Adsumilli, B., & Bovik, A. C. (2020) · arXiv · doi:10.48550/arxiv.2007.11634 · Cited by 69
Self-citationImage Super-Resolution Quality Assessment: Structural Fidelity Versus Statistical Naturalness
Zhou, W., Wang, Z., & Chen, Z. (2021) · International Conference on Quality of Multimedia Experience (QoMEX) · doi:10.1109/qomex51781.2021.9465479 · Cited by 69
Chimp optimization algorithm in multilevel image thresholding and image clustering
Eisham, Z. K., Haque, M. M., Rahman, M. S., Nishat, M. M., Faisal, F., & Islam, M. R. (2022) · Evolving Systems · doi:10.1007/s12530-022-09443-3 · Cited by 68
“Mittal et al. (2013) MATLAB (2021)”
CBLA: Color-Balanced Locally Adjustable Underwater Image Enhancement
Jha, M., & Bhandari, A. K. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3396850 · Cited by 68
“Comparative (a) PCQI [44], (b) CEIQ [45], (c) CCF [47], and (d) NIQE [46] boxplots for the proposed method using UIQS dataset [35].”
BackgroundMethodInfluentialBridging the Gap Between Haze Scenarios: A Unified Image Dehazing Model
Feng, Y., Su, Z., Ma, L., Li, X., Liu, R., & Zhou, F. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3414677 · Cited by 68
“5 [89], perceptual non-reference image quality evaluator PIQE, 1 neural network-based quality evaluator NIMA [90], image Entropy 2 assessment index, natural image quality evaluator NIQE [91], and blind image quality metric for enhanced images BIQME [92].”
Seeing the Unseen: A Frequency Prompt Guided Transformer for Image Restoration
Zhou, S., Pan, J., Shi, J., Chen, D., Qu, L., & Yang, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72640-8_14 · Cited by 68
Quality Assessment of Sharpened Images: Challenges, Methodology, and Objective Metrics
Krasula, L., Callet, P. L., Fliegel, K., & Klima, M. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2651374 · Cited by 68
An Evaluation of Video Quality Assessment Metrics for Passive Gaming Video Streaming
Barman, N., Schmidt, S., Zadtootaghaj, S., Martini, M. G., & Möller, S. (2018) · Proceedings of the 23rd Packet Video Workshop · doi:10.1145/3210424.3210434 · Cited by 61
“Natural Image ality Evaluator (NIQE) is a learning-based NR quality estimation metric which uses statistical features based on the space domain NSS model [12].”
MethodGeneration-Based Joint Luminance-Chrominance Learning for Underwater Image Quality Assessment
Wang, Z., Shen, L., Wang, Z., Lin, Y., & Jin, Y. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3212788 · Cited by 67
“…SROCC, PLCC and KROCC and the lowest RMSE in evaluating images enhanced by almost any enhancement [1], UIQM [2] (UICM, UISM AND UIC ON M), NIQE [19], CCF [32], NUIQ [34], R ES N ET -50, D ENSE N ET -121, B-FEN [28] AND O UR P ROPOSED GLCQE ON I MAGES E NHANCED BY ACPAB [37], HP [7], IBLA [35],…”
BackgroundMethodInfluentialModular Blind Video Quality Assessment
Wen, W., Li, M., Zhang, Y., Liao, Y., Li, J., Zhang, L., & Ma, K. (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/cvpr52733.2024.00267 · Cited by 68
“In order to examine the effects of spatial resolution changes, we choose two conventional models, NIQE [23] and BRISQUE [22], which utilize features extracted from the full-size resolution.”
MethodSF-IQA: Quality and Similarity Integration for AI Generated Image Quality Assessment
Yu, Z., Guan, F., Lu, Y., Li, X., & Chen, Z. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00663 · Cited by 67
“No-Reference IQA (NR-IQA), which evaluates image quality without reference images, presents a more complex yet universally applicable approach [6, 14, 18, 21–23, 31, 32, 63].”
BackgroundMethodInfluentialKnowledge-Driven Deep Unrolling for Robust Image Layer Separation
Liu, R., Jiang, Z., Fan, X., & Luo, Z. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2921597 · Cited by 67
“Here, natural image quality evaluator [62] (NIQE) is employed since the problem of low-light image enhancement has no ground truth.”
BackgroundNTIRE 2021 Challenge on Perceptual Image Quality Assessment
Gu, J., Cai, H., Dong, C., Ren, J., Qiao, Y., Gu, S., Timofte, R., Cheon, M., Yoon, S., Kang, B., et al. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00077 · Cited by 67
High-quality Image Dehazing with Diffusion ModelPreprint
Yu, H., Huang, J., Zheng, K., & Zhao, F. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.11949 · Cited by 67
“We evaluate our method on six different metrics: FID [63], LPIPS [64], PSNR, SSIM [65], BRISQUE [66], and NIQE [67], in which FID and LPIPS are perceptual-based metrics, PSNR and SSIM are distortion-based metrics, BRISQUE and NIQE are two well-known no-reference image quality assessment indicators.”
MethodDeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows
Wolf, V., Lugmayr, A., Danelljan, M., Gool, L. V., & Timofte, R. (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/cvpr46437.2021.00016 · Cited by 66
Stealing Machine Learning Models: Attacks and Countermeasures for Generative Adversarial Networks
Hu, H., & Pang, J. (2021) · Annual Computer Security Applications Conference · doi:10.1145/3485832.3485838 · Cited by 66
Low-Illumination Image Enhancement Based on Deep Learning Techniques: A Brief Review
Tang, H., Zhu, H., Fei, L., Wang, T., Cao, Y., & Xie, C. (2023) · Photonics · doi:10.3390/photonics10020198 · Cited by 67
“…SSIM (Structural Similarity Index) [94] Full-Reference IE (Information Entropy) [95] Non-Reference NIQE (Natural Image Quality Evaluator) [96] Non-Reference LOE (Lightness Order Error) [97] Full-Reference PI (Perceptual Index) [98] Non-Reference MUSIQ (Multi-scale Image Quality…”
Super-resolution of magnetic resonance images using Generative Adversarial Networks
Guerreiro, J., Tomás, P., Garcia, N. C., & Aidos, H. (2023) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2023.102280 · Cited by 66
Lin, Y., Tian, Y., Chen, S., Fu, Z., Wang, Y., Chai, W., Xing, Z., Li, W., Zhu, L., & Ding, X. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i5.32564 · Cited by 66
Ensemble learning on visual and textual data for social image emotion classification
Corchs, S., Fersini, E., & Gasparini, F. (2017) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-017-0734-0 · Cited by 66
“…and visual perception: feature congestion and subband entropy [37], image complexity [38], image blur [39], entropy, edge contrast and measure of enhancement [40], a general purpose image quality metric, NIQE [41], a noise metric [42], a measure of the degree of focus [43], all of them 1-”
BackgroundMultiscale modeling of shale samples based on low- and high-resolution images
Wu, Y., Tahmasebi, P., Lin, C., Ren, L., & Dong, C. (2019) · Marine and Petroleum Geology · doi:10.1016/j.marpetgeo.2019.06.006 · Cited by 66
MRI Super-Resolution with GAN and 3D Multi-Level DenseNet: Smaller, Faster, and BetterPreprint
Chen, Y., Christodoulou, A., Zhou, Z., Shi, F., Xie, Y., & Li, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.01217 · Cited by 67
“GAN even obtained a higher score in NIQE and PI than HR, since SR images were generated from less noisy LR input, making the SR more plausible for noise-sensitive perceptual metrics.”
MethodHuang, Z., Huang, L., Li, Q., Zhang, T., & Sang, N. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.06.063 · Cited by 65
Chiu, T.-Y., & Gurari, D. (2022) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv51458.2022.00303 · Cited by 66
Comparison of single image HDR reconstruction methods — the caveats of quality assessment
Hanji, P., Mantiuk, R., Eilertsen, G., Hajisharif, S., & Unger, J. (2022) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3528233.3530729 · Cited by 65
Semi-Supervised Domain Alignment Learning for Single Image Dehazing
Yu, D., Li, Y., Dong, Q., Zhang, H., & Chen, S. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2022.3221544 · Cited by 65
“4) No Reference Image Quality Assessments: We test four well-known no-reference image quality assessment (NR-IQA) indicators: 1) BRISQUE [64]; 2) NIQE [65]; 3) fog aware density evaluator (FADE) [24]; and 4) dehazing quality index (DHQI) [62].”
BackgroundMethodResultSemi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution
Hou, H., Xu, J., Hou, Y., Hu, X., Wei, B., & Shen, D. G. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3240845 · Cited by 65
“On two real-world test sets, we also use the widely used Natural Image Quality Evaluator (NIQE) [76] to evaluate the naturalness of restored face images.”
MethodDeep Blind Super-Resolution for Satellite Video
Xiao, Y., Yuan, Q., Zhang, Q., & Zhang, L. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3291822 · Cited by 65
“In real-world experiments, the reference-free metric natural image quality evaluator (NIQE) [75] is adopted.”
Machine learning for shipwreck segmentation from side scan sonar imagery: Dataset and benchmark
Sethuraman, A. V., Sheppard, A., Bagoren, O., Pinnow, C., Anderson, J., Havens, T. C., & Skinner, K. A. (2024) · The International Journal of Robotics Research · doi:10.1177/02783649241266853 · Cited by 65
Low-light image enhancement: A comprehensive review on methods, datasets and evaluation metrics
Jingchun, Z., Su, G. E., & Sunar, M. S. (2024) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2024.102234 · Cited by 65
VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis
Corona, E., Zanfir, A., Băzăvan, E. G., Kolotouros, N., Alldieck, T., & Sminchisescu, C. (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/cvpr52734.2025.01482 · Cited by 65
“For image quality, the FID score [27] measures the distance between ground-truth and generated image distributions, while the Cumulative Probability of Blur Detection (CPBD) [50, 51] and Natural Image Quality Evaluator (NIQE) [48] validate the quality of generated images.”
LMM4LMM: Benchmarking and Evaluating Large-Multimodal Image Generation With LMMs
Wang, J., Duan, H., Zhao, Y., Wang, J., Zhai, G., & Min, X. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.01608 · Cited by 66
Deep learning network for blind image quality assessment
Gu, K., Zhai, G., Yang, X., & Zhang, W. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025102 · Cited by 65
“In [21] and [24], Mittal et al . utilized the classical NSS model in the spatial domain [26], which can validly capture the essential low-order statistics of natural images.”
BackgroundMethodEstimation of Gaussian, Poissonian-Gaussian, and Processed Visual Noise and its Level Function
Rakhshanfar, M., & Amer, M. A. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2588320 · Cited by 66
“MetricQ AND NIQE COMPARISON OF PGN REMOVAL Fig.”
MethodContinuous Prediction of Streaming Video QoE Using Dynamic Networks
Bampis, C. G., Li, Z., & Bovik, A. C. (2017) · IEEE Signal Processing Letters · doi:10.1109/lsp.2017.2705423 · Cited by 65
Self-citationReal‐world super‐resolution of face‐images from surveillance cameras
Aakerberg, A., Nasrollahi, K., & Moeslund, T. B. (2021) · IET Image Processing · doi:10.1049/ipr2.12359 · Cited by 64
No-Reference Image Quality Assessment via Multibranch Convolutional Neural Networks
Pan, Z., Yuan, F., Wang, X., Xu, L., Shao, X. J., & Kwong, S. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2022.3146804 · Cited by 64
“The traditional universal NR-IQA methods are based on hand-crafted features such as natural scene statistics (NSS) features [12]–[16].”
MethodGeetha, G. K., & Sim, S. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104572 · Cited by 66
Zhang, H., Tang, L., Xiang, X., Zuo, X., & Ma, J. (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/cvpr52733.2024.02501 · Cited by 64
“For the ExDark dataset lacking ground truth, we utilize non-reference metrics NIQE [31] and PIQE [40], while for the AGLIE dataset with ground truth, we use well-known SSIM and PSNR. Fig.”
MethodReal-World Remote Sensing Image Dehazing: Benchmark and Baseline
Zhu, Z.-H., Lu, W., Chen, S.-B., Ding, C. H. Q., Tang, J., & Luo, B. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3584234 · Cited by 64
“To further validate generalization capability in real-world scenarios, we additionally utilized nat-ural image quality evaluator (NIQE) [61] and integrated local NIQE (IL-NIQE) [62] metrics, where lower values indicate better perceptual quality without requiring reference images.”
Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption
Du, C., Wu, T., Ma, K., & Zhang, L. (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/cvpr52734.2025.01189 · Cited by 67
“…models that mimic the Human Visual System (HVS) in perceiving image quality [45], which can be broadly classified into two categories based on the availability of reference images: Full-Reference IQA (FR-IQA) [5, 6, 44, 45, 55, 58] and No-Reference IQA (NR-IQA) [25, 43, 48, 51, 60, 61].”
Wang, J., Duan, H., Zhai, G., Wang, J., & Min, 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/cvpr52734.2025.01758 · Cited by 64
Deep Objective Quality Assessment Driven Single Image Super-Resolution
Yan, B., Bare, B., Ma, C., Li, K., & Tan, W. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2914883 · Cited by 64
“PI value is the combination of Ma et al. [28] and NIQE [52], namely PI = ((10−Ma) +NIQE)/2 (lower is better).”
BackgroundConfidence Measure Guided Single Image De-Raining
Yasarla, R., & Patel, V. M. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2973802 · Cited by 64
“To this end, we use the Natural Image Quality Evaluator (NIQE) no-reference image quality score [19] and formulate a joint task of estimating the level of distortion at each spatial location of the image and computing rain streak information to reconstruct the clean image.”
MethodInfluentialImproved Method for Enhancing Dark Images based on CLAHE and Morphological Reconstruction
A, M. R., Koshy, G., & Simon, P. (2019) · Procedia Computer Science · doi:10.1016/j.procs.2020.01.033 · Cited by 64
Journey Towards Tiny Perceptual Super-Resolution
Lee, R., Dudziak, Ł., Abdelfattah, M. S., Venieris, S. I., Kim, H., Wen, H., & Lane, N. D. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58574-7_6 · Cited by 64
Assessing Image Quality Issues for Real-World Problems
Chiu, T.-Y., Zhao, Y., & Gurari, D. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00370 · Cited by 63
Low-Light Image Enhancement With Regularized Illumination Optimization and Deep Noise Suppression
Guo, Y., Lu, Y., Liu, R. W., Yang, M., & Chui, K. T. (2020) · IEEE Access · doi:10.1109/access.2020.3015217 · Cited by 64
“Meanwhile, two popular no-reference image quality assessment methods, i.e., natural image quality evaluator (NIQE) [67] and blind tone-mapped quality index (BTMQI) [68] are also employed to perform blind image quality evaluation in realistic experiments.”
MethodMadhusudana, P. C., Birkbeck, N., Wang, Y., Adsumilli, B., & Bovik, A. C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3106801 · Cited by 63
“This observation is rather unconventional, given that in many prior models [4], [6], [33], [34] it is assumed that divisive normalization tends to capture underlying distortions because they also predict the empirical distributions of the processed image or video signals.”
BackgroundSelf-citationVijayalakshmi, D., & Nath, M. K. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-13932-7 · Cited by 63
“5 NIQE [28] 6 displays the mean discrete entropy (DE) value of the input and processed images obtained from the techniques described in the literature inclusive of proposed algorithm.”
MethodInfluentialUncertainty-Based Thin Cloud Removal Network via Conditional Variational Autoencoders
Ding, H., Zi, Y., & Xie, F. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-26313-2_4 · Cited by 63
“We use full-reference image quality evaluation metrics PSNR and SSIM [33] and no-reference evaluation metrics NIQE [34] and BRISQUE [35] for quantitative evaluation.”
MethodHan, G., Wang, M., Zhu, H., & Lin, C. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3281741 · Cited by 63
“Since the URPC and SQUID datasets do not have reference images, we used non-reference metrics such as underwater image quality measures (UIQM) [56], underwater color image quality evaluation (UCIQE) [57], and naturalness image quality eval-uator (NIQE) [58] to evaluate the model.”
MethodMultiscale Underwater Image Enhancement in RGB and HSV Color Spaces
Liu, C., Shu, X., Pan, L., Shi, J., & Han, B. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3298395 · Cited by 63
“NIQE is based on the space domain natural scene statistic (NSS) model [42].”
MethodZhang, D., Wu, C., Zhou, J., Zhang, W., Lin, Z., Polat, K., & Alenezi, F. S. (2023) · Neural Networks · doi:10.1016/j.neunet.2023.11.008 · Cited by 63
DiffStega: Towards Universal Training-Free Coverless Image Steganography with Diffusion Models
Yang, Y., Liu, Z., Jia, J., Gao, Z., Li, Y., Sun, W., Liu, X., & Zhai, G. (2024) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2024/175 · Cited by 63
“We use NIQE [Mittal et al. , 2012] to blindly assess the naturalness of encrypted images.”
MethodExtracting Noise and Darkness: Low-Light Image Enhancement via Dual Prior Guidance
Wang, H., Yan, X., Hou, X., Zhang, K., & Dun, Y. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3480930 · Cited by 63
Advancing image super-resolution techniques in remote sensing: A comprehensive survey
Qi, Y., Lou, M., Liu, Y., Li, L., Yang, Z., & Nie, W. (2025) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2025.10.024 · Cited by 64
“(4) Natural Image Quality Evaluator (NIQE): NIQE [374] is a no-reference image quality evaluation metric.”
Wavelet-based physically guided normalization network for real-time traffic dehazing
Zhang, S., Zhang, X., Shen, L., Wan, S., & Ren, W. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112451 · Cited by 65
Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment
Wu, T., Shi, S., Cai, H., Cao, M., Xiao, J., Zheng, Y., & Yang, Y. (2023) · neural information processing systems · doi:10.52202/075280-2834 · Cited by 63
Perceptual Attacks of No-Reference Image Quality Models with Human-In-The-Loop
Zhang, W., Li, D., Min, X., Zhai, G., Guo, G., Yang, X., & Ma, K. (2022) · neural information processing systems · doi:10.52202/068431-0211 · Cited by 65
Sand-Dust Image Enhancement Using Successive Color Balance With Coincident Chromatic Histogram
Park, T. H., & Eom, I. K. (2021) · IEEE Access · doi:10.1109/access.2021.3054899 · Cited by 63
“Furthermore, 4 conventional non-reference quality measures, including the naturalness image quality evaluator (NIQE) [34], no-reference perception-based image quality evaluator (PIQUE) [35], blind/referenceless image spatial quality evaluator (BRISQUE) [36], and no-reference image quality metric…”
BackgroundBlind Image Quality Assessment Based on Rank-Order Regularized Regression
Wu, Q., Li, H., Wang, Z., Meng, F., Luo, B., Li, W., & Ngan, K. N. (2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2700206 · Cited by 62
“Both the proposed method with and without R3 are compared with classical full-reference (FR) IQA metrics (PSNR, SSIM [54]), and state-of-the-art BIQA metrics (BIQI [36], DIIVINE [8], BLINDS-II [49], BRISQUE [7], NIQE [14] and QAC [55]).”
MethodInfluentialRahman, Z.-U., Pu, Y., Aamir, M., & Wali, S. (2020) · The Visual Computer · doi:10.1007/s00371-020-01838-0 · Cited by 62
No-Reference Screen Content Image Quality Assessment With Unsupervised Domain Adaptation
Chen, B., Li, H., Fan, H., & Wang, S. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3084750 · Cited by 62
Twice Mixing: A rank learning based quality assessment approach for underwater image enhancement
Fu, Z., Fu, X., Huang, Y., & Ding, X. (2021) · Signal Processing Image Communication · doi:10.1016/j.image.2021.116622 · Cited by 64
Low-light image enhancement based on sharpening-smoothing image filter
Demir, Y., & Kaplan, N. H. (2023) · Digital Signal Processing · doi:10.1016/j.dsp.2023.104054 · Cited by 62
LIEDNet: A Lightweight Network for Low-Light Enhancement and Deblurring
Liu, M., Cui, Y., Ren, W., Zhou, J., & Knoll, A. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3541429 · Cited by 63
Benchmarking Multi-dimensional AIGC Video Quality Assessment: A Dataset and Unified Model
Zhang, Z., Sun, W., Li, X., Jia, J., Min, X., Zhang, Z., Li, C., Chen, Z., Wang, P., Sun, F., et al. (2025) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3749844 · Cited by 62
“Specifically, we select four knowledge-driven IQA metrics, including two NSS-based methods, NIQE [60] and BRISQUE [59], and two deep features-based methods, IS [67] and FID [28].”
When Schrödinger Bridge Meets Real-World Image Dehazing with Unpaired Training
Lan, Y., Cui, Z., Luo, X., Liu, C., Wang, N., Zhang, M., Su, Y., & Liu, D. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00819 · Cited by 62
“For images without GT, we use no-reference metrics, including FID [17], NIQE [29], MUSIQ [19], and MANIQA [42].”
Arbitrarily-Oriented Text Detection in Low Light Natural Scene Images
Xue, M., Shivakumara, P., Zhang, C., Yao, X. L., Lü, T., Pal, U., Lopresti, D., & Yang, Z. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.3015037 · Cited by 62
Raake, A., Borer, S., Satti, S. M., Gustafsson, J., Rao, R. R. R., Medagli, S., List, P., Göring, S., Lindero, D., Robitza, W., et al. (2020) · IEEE Access · doi:10.1109/access.2020.3032080 · Cited by 62
DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution ModelsPreprint
Xie, L., Wang, X., Chen, X., Li, G., Shan, Y., Zhou, J., & Dong, C. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2307.02457 · Cited by 62
“The unreliable of NIQE (Mittal et al., 2012) and MANIQA (Yang et al., 2022) metrics on evaluating the performance of artifacts removal (referring to Tab.”
BackgroundMethodInfluentialVideo Quality Assessment: A Comprehensive SurveyPreprint
Zheng, Q., Fan, Y., Huang, L., Zhu, T., Liu, J., Hao, Z., Xing, S., Chen, C.-J., Min, X., Bovik, A. C., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.04508 · Cited by 63
“Therefore, “opinion-unaware” (OU) or “completely blind” models which do not rely on training on human-labeled videos, have aroused considerable research insterest [47], [203], [206]– [210].”
InfluentialSelf-citationQuality-Aware Unpaired Image-to-Image Translation
Chen, L., Wu, L., Hu, Z., & Wang, M. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2907052 · Cited by 62
“A smaller score of NIQE indicates better perceptual quality, so we change the classical IQA loss function in Eq.”
BackgroundMethodInfluentialAdaptive Weighted Graph Approach to Generate Multimodal Cancelable Biometric Templates
Walia, G. S., Jain, G., Bansal, N., & Singh, K. (2019) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2954779 · Cited by 61
“Evaluation (NIQE) technique proposed in [35].”
Efficient Image Enhancement Model for Correcting Uneven Illumination Images
Rahman, Z.-U., Pu, Y., Aamir, M., Wali, S., & Guan, Y. (2020) · IEEE Access · doi:10.1109/access.2020.3001206 · Cited by 61
“The quantitative performance of proposed model is evaluated on four commonly used metrics such as discrete entropy (DE) [49], natural image quality evaluator (NIQE) [50], visual information fidelity (VIF) [51] and visibility level descriptor (VLD) [52].”
MethodA Locally Optimized Model for Hyperspectral and Multispectral Images Fusion
Ren, K., Sun, W., Meng, X., Yang, G., Peng, J., & Huang, J. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3133670 · Cited by 61
An Empirical Study on Retinex Methods for Low-Light Image Enhancement
Rasheed, M. T., Guo, G., Shi, D., Khan, H., & Cheng, X. (2022) · Remote Sensing · doi:10.3390/rs14184608 · Cited by 62
Attentive Deep Image Quality Assessment for Omnidirectional Stitching
Duan, H., Min, X., Sun, W., Zhu, Y., Zhang, X.-P. S., & Zhai, G. (2023) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2023.3250956 · Cited by 61
“[75], NIQE [30], CORNIA [76], QAC [77], ILNIQE [78], LPSI [79], HOSA [80], DipIQ [81], Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
BackgroundMethod
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.