Making a “Completely Blind” Image Quality Analyzer
The DOI matches its Crossref record; 19 of the 19 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].”
MethodMartin, 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-citationThe statistics of natural images
Ruderman, D. (1994) · Network: Computation in Neural Systems · doi:10.1088/0954-898x/5/4/006 · Cited by 941 · cited 2×
“The coefficients (1) have been observed to reliably follow a Gaussian distribution when computed from natural images that have suffered little or no apparent distortion [10].”
BackgroundMethod
Research works printed but not linked: 1
- 2012, Image obsessed, National Geographic, 221, 35
Cited by
Items 101–200 of 1,012
Image Quality Assessment Using Contrastive Learning
Madhusudana, P. C., Birkbeck, N., Wang, Y., Adsumilli, B., & Bovik, A. C. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3181496 · Cited by 285
“In this section we review related work from the literature concerning NR-IQA and self-supervised learning.”
BackgroundMethodInfluentialSelf-citationSingle Image Deraining: From Model-Based to Data-Driven and Beyond
Yang, W., Tan, R. T., Wang, S., Fang, Y., & Liu, J. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2995190 · Cited by 284
Kim, J., Zeng, H., Ghadiyaram, D., Lee, S., Zhang, L., & Bovik, A. C. (2017) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2736018 · Cited by 283
“Since we have found no serious attempts to use unsupervised deep models, we make no comparisons of this type, although the success of the very simple model [31] suggests this is an interesting research direction.”
BackgroundSelf-citationBlind image quality assessment by relative gradient statistics and adaboosting neural network
Liu, L., Hua, Y., Zhao, Q., Huang, H., & Bovik, A. C. (2016) · Signal Processing: Image Communication · doi:10.1016/j.image.2015.10.005 · Cited by 282
“further utilized the image features in BRISQUE to develop trainingfree IQA models [31,48].”
MethodSelf-citationEDiffSR: An Efficient Diffusion Probabilistic Model for Remote Sensing Image Super-Resolution
Xiao, Y., Yuan, Q., Jiang, K., He, J., Jin, X., & Zhang, L. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3341437 · Cited by 280
Generative Diffusion Prior for Unified Image Restoration and Enhancement
Fei, B., Lyu, Z., Pan, L., Zhang, J., Yang, W., Luo, T., Zhang, B., & Dai, B. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00958 · Cited by 279
“As shown in Table 3, our GDP-x0 fulfills the best FID, lightness order error (LOE) [85], and perceptual index (PI) [57] across all the zero-shot methods under three datasets.”
BackgroundMethodInfluentialLightening Network for Low-Light Image Enhancement
Wang, L.-W., Liu, Z.-S., Siu, W.-C., & Lun, D. P. K. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3008396 · Cited by 278
“Recently, some metrics [36]–[39] have been proposed which focus on the visual quality evaluation.”
BackgroundExploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Pan, X., Zhan, X., Dai, B., Lin, D., Loy, C. C., & Luo, P. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3115428 · Cited by 277
“We reported widely used NIQE [27], PSNR, and RMSE scores.”
MethodOn the use of deep learning for blind image quality assessment
Bianco, S., Celona, L., Napoletano, P., & Schettini, R. (2018) · Signal, Image and Video Processing · doi:10.1007/s11760-017-1166-8 · Cited by 277
TOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment
Chen, C., Mo, J., Hou, J., Wu, H., Liao, L., Sun, W., Yan, Q., & Lin, W. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3378466 · Cited by 276
“Min et al. [34], [35] proposed new features based on pseudo-reference image and significantly outperforms NSS based methods.”
MethodInfluentialAn imaging-inspired no-reference underwater color image quality assessment metric
Wang, Y., Li, N., Li, Z., Gu, Z., Zheng, H., Zheng, B., & Sun, M. (2018) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2017.12.006 · Cited by 273
Contrastive Semi-Supervised Learning for Underwater Image Restoration via Reliable Bank
Huang, S., Wang, K., Liu, H., Chen, J., & Li, Y. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01740 · Cited by 273
No-Reference Image Blur Assessment Based on Discrete Orthogonal Moments
Li, L., Lin, W., Wang, X., Yang, G., Bahrami, K., & Kot, A. C. (2016) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2015.2392129 · Cited by 270
“ity evaluator (NIQE) [25].”
Underwater Image Enhancement Quality Evaluation: Benchmark Dataset and Objective Metric
Jiang, Q., Gu, Y., Li, C., Cong, R., & Shao, F. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3164918 · Cited by 266
“…such a kind include LGS [32], BIQI [33], BRISQUE [34], BLIINDS-II [35], DIIVINE [36], OG-IQA [37], SSEQ [38], GM-LOG [39], NRSL [40], GWH-GLBP [41], BMPRI [42], NFERM [43], PIQE [44], FRIQUEE [45], BIQME [46], RISE [31], PCRL [47], NIQE [48], ILNIQE [49], NIQMC [50], MFILGN [51], and NR-LFQA [52].”
BackgroundUnsupervised Single Image Dehazing Using Dark Channel Prior Loss
Golts, A., Freedman, D., & Elad, M. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2952032 · Cited by 264
“A completely unsupervised alternative may be suggested, optimizing a no-reference perceptual quality score as NIQE [37], requiring no supervision whatsoever, but naturally leading to higher distortion.”
BackgroundMethodInfluentialRe-IQA: Unsupervised Learning for Image Quality Assessment in the Wild
Saha, A., Mishra, S., & Bovik, A. C. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00566 · Cited by 262
“For example, the NSS-based BRISQUE [19] and NIQE [20] models obtain features that capture in a normalized bandpass space [26].”
MethodSelf-citationImplicit Neural Representation for Cooperative Low-light Image Enhancement
Yang, S., Ding, M., Wu, Y., Li, Z., & Zhang, J. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01187 · Cited by 261
“In general, a higher PSNR or SSIM means more authentic restored results, while a lower NIQE or LOE represents higher quality details, lightness, and tone.”
MethodDeblurring via Stochastic Refinement
Whang, J., Delbracio, M., Talebi, H., Saharia, C., Dimakis, A. G., & Milanfar, P. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01581 · Cited by 259
“We evaluate our method on four different perceptual metrics: LPIPS [77], NIQE [49], FID (Fréchet Inception Distance) [24], and KID (Kernel Inception Distance) [4].”
MethodPredicting the Perceptual Quality of Point Cloud: A 3D-to-2D Projection-Based Exploration
Yang, Q., Chen, H., Ma, Z., Xu, Y., Tang, R., & Sun, J. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.3033117 · Cited by 256
“For comparative studies, we have also included the PSNR, PSNR-HVS-M [63], SSIM [19], MS-SSIM [18], IWSSIM [64], FSIM [52], VIF [65] as full reference examples, and NIQE [66], IL-NIQE [67] and OG-IQA [68] as no reference representatives.”
MethodUncertainty Inspired Underwater Image Enhancement
Fu, Z., Wang, W., Huang, Y., Ding, X., & Ma, K.-K. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19797-0_27 · Cited by 256
Frequency Separation for Real-World Super-Resolution
Fritsche, M., Gu, S., & Timofte, R. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00445 · Cited by 252
“We use the pre-trained weights based on the NIQE metric [28].”
MethodQ-Instruct: Improving Low-Level Visual Abilities for Multi-Modality Foundation Models
Wu, H., Zhang, Z., Zhang, E., Chen, C., Liao, L., Wang, A., Xu, K., Li, C., Hou, J., Zhai, G., et al. (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/cvpr52733.2024.02408 · Cited by 251
Low-light Image Enhancement via Breaking Down the Darkness
Guo, X., & Hu, Q. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-022-01667-9 · Cited by 249
“Image quality assessment metrics, including PSNR, SSIM, NIQE [17], DeltaE [19] and LOE [24], are employed to measure these methods.”
Sagan, V., Maimaitijiang, M., Sidike, P., Eblimit, K., Peterson, K., Hartling, S., Esposito, F., Khanal, K., Newcomb, M., Pauli, D., et al. (2019) · Remote Sensing · doi:10.3390/rs11030330 · Cited by 249
Low-Light Image Enhancement via Progressive-Recursive Network
Li, J., Feng, X., & Hua, Z. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3049940 · Cited by 247
Low-Light Image Enhancement with Wavelet-Based Diffusion Models
Jiang, H., Luo, A., Fan, H., Han, S., & Liu, S. (2023) · ACM Transactions on Graphics · doi:10.1145/3618373 · Cited by 246
Screen Content Quality Assessment: Overview, Benchmark, and Beyond
Min, X., Gu, K., Zhai, G., Yang, X., Zhang, W., Le Callet, P., & Chen, C. W. (2022) · ACM Computing Surveys · doi:10.1145/3470970 · Cited by 246
Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision
Wu, H., Zhang, Z., Zhang, E., Chen, C., Liao, L., Wang, A., Li, C., Sun, W., Yan, Q., Zhai, G., et al. (2023) · International Conference on Learning Representations · doi:10.48550/arxiv.2309.14181 · Cited by 246
“Dataset Type In-the-wild Generated Artificial Model / Dataset KONiQ-10k SPAQ LIVE-FB LIVE-itw CGIQA-6K AGIQA-3K KADID-10K NIQE (Mittal et al., 2013) 0.”
BackgroundMSR-net:Low-light Image Enhancement Using Deep Convolutional Network
Shen, L. C., Yue, Z., Feng, F., Chen, Q., Liu, S., & Ma, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.02488 · Cited by 245
“Since the ground truth is known for the synthetic test data, we use SSIM [31] for a quantitative evaluation and NIQE [22] to assess the natural preservation.”
MethodGu, K., Wang, S., Zhai, G., Ma, S., Yang, X., Lin, W., Zhang, W., & Gao, W. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2518868 · Cited by 244
“The sixth one is the NIQE [21], which does not apply any prior knowledge of contents or distortions but rather than measures the deviations from statistical regularities of natural images to predict quality.”
BackgroundMethodHierarchical dense recursive network for image super-resolution
Jiang, K., Wang, Z., Yi, P., & Jiang, J. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107475 · Cited by 243
No-Reference Quality Assessment of Screen Content Pictures
Gu, K., Zhou, J., Qiao, J.-F., Zhai, G., Lin, W., & Bovik, A. C. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2711279 · Cited by 242
“Motivated by well-known Natural Scene Statistics (NSS) models [11], a variety of blind picture quality models [12], including BLIINDS-II [13], BRISQUE [14], C-DIIVINE [15], LPSI [16], NIQE [17] and IL-NIQE [18], have been developed.”
BackgroundMethodInfluentialSelf-citationA Deep Learning based No-reference Quality Assessment Model for UGC Videos
Sun, W., Min, X., Lu, W., & Zhai, G. (2022) · Proceedings of the 30th ACM International Conference on Multimedia · doi:10.1145/3503161.3548329 · Cited by 240
“• IQAmodels: NIQE [24], BRISQUE [22], GM-LOG [41], VGG19 [27], ResNet50 [7], and KonCept512 [9].”
MethodInfluentialQoE Management of Multimedia Streaming Services in Future Networks: A Tutorial and Survey
Barakabitze, A. A., Barman, N., Ahmad, A., Zadtootaghaj, S., Sun, L., Martini, M. G., & Atzori, L. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2958784 · Cited by 239
“Peak Signal-to-Noise Ratio (PSNR) [49] FR Images - Frames Structural Similarity Index Metric (SSIM) [44] 2004 FR Images - Frames Video Multimethod Assessment Fusion (VMAF) [45] 2016 FR Images - Frames Visual Information Fidelity (VIF) [50] 2006 FR Images - Frames HDR-VDP-2: A calibrated visual metric for visibility an…”
Perceptual Quality Assessment of Screen Content Images
Yang, H., Fang, Y., & Lin, W. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2465145 · Cited by 238
“For example, when we capture SCIs by smart phones, blurring appears on images along with hand-shake or out-of-focus of camera.”
BackgroundInvestigating Tradeoffs in Real-World Video Super-Resolution
Chan, K. C. K., Zhou, S., Xu, X., & Loy, C. C. (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/cvpr52688.2022.00587 · Cited by 238
TBEFN: A Two-Branch Exposure-Fusion Network for Low-Light Image Enhancement
Lu, K., & Zhang, L. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.3037526 · Cited by 237
ARNIQA: Learning Distortion Manifold for Image Quality Assessment
Agnolucci, L., Galteri, L., Bertini, M., & Bimbo, A. D. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00026 · Cited by 235
“Traditional methods [20–22, 35, 41], such as BRISQUE [20] and NIQE [21], rely on the extraction of handcrafted features from the images.”
MethodDomain Adaptation for Underwater Image Enhancement
Wang, Z., Shen, L., Xu, M., Yu, M., Wang, K., & Lin, Y. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3244647 · Cited by 231
“NIQE [53], CCF [54] and NUIQ [55]) and learning-based”
BackgroundDarkIR: Robust Low-Light Image Restoration
Feijoo, D., Benito, J. C., Garcia, A., & Conde, M. V. (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/cvpr52734.2025.01016 · Cited by 231
“We employ recent image quality assessment methods: MUSIQ [23], NRQM [34] and NIQE [36] as our perceptual metrics.”
Xiao, Y., Yuan, Q., Jiang, K., He, J., Wang, Y., & Zhang, L. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.03.021 · Cited by 229
“Here we adopt a reference-free indicator NIQE [80] to evaluate these methods objectively.”
No-Reference Quality Assessment for Multiply-Distorted Images in Gradient Domain
Li, Q., Lin, W., & Fang, Y. (2016) · IEEE Signal Processing Letters · doi:10.1109/lsp.2016.2537321 · Cited by 229
“[35], GMLOG [36], NFERM [37], NIQE [29], ILNIQE [30], and SISBLM [8].”
BackgroundPractical Blind Image Denoising via Swin-Conv-UNet and Data Synthesis
Zhang, K., Li, Y., Liang, J., Cao, J., Zhang, Y., Tang, H., Fan, D.-P., Timofte, R., & Gool, L. V. (2023) · Machine Intelligence Research · doi:10.1007/s11633-023-1466-0 · Cited by 228
“Visual results and no-reference image quality assessment metrics (NIQE ↓ /NRQM ↑ /PIQE ↓ ) results of different methods for real image denoising.”
Learning Multi-Scale Photo Exposure Correction
Afifi, M., Derpanis, K. G., Ommer, B., & Brown, M. S. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00904 · Cited by 228
“Summary of NIQE scores [48] on different low-light image datasets.”
BackgroundMethodInfluentialUCL-Dehaze: Toward Real-World Image Dehazing via Unsupervised Contrastive Learning
Wang, Y., Yan, X., Wang, F. L., Xie, H., Yang, W., Zhang, X.-P., Qin, J., & Wei, M. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3362153 · Cited by 228
“For the quantitative comparison, we employ four well-known no-reference image quality assessment metrics: NIQE (Mittal et al, 2013), BRISQUE (Mittal et al, 2012), SSEQ (Liu et al, 2014), and PI (Blau et al, 2018).”
MethodCVD2014—A Database for Evaluating No-Reference Video Quality Assessment Algorithms
Nuutinen, M., Virtanen, T., Vaahteranoksa, M., Vuori, T., Oittinen, P., & Hakkinen, J. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2562513 · Cited by 227
“Metric Description BIQI [44] Image quality metric BRISQUE [45] Image quality metric NIQE [46] Image quality metric DESIQUE [47] Image quality metric FISH [48] Image sharpness metric S3 [49] Image sharpness metric LPC [50] Image sharpness metric CPBD [63] Image sharpness metric Video BLIINDS [51] LIVE video database (v…”
BackgroundHybrid No-Reference Quality Metric for Singly and Multiply Distorted Images
Gu, K., Zhai, G., Yang, X., & Zhang, W. (2014) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2014.2344471 · Cited by 227
“• NIQE [34], predicts the image quality nearly without any prior knowledge of contents or distortions.”
BackgroundMethodInfluentialIDE: Image Dehazing and Exposure Using an Enhanced Atmospheric Scattering Model
Ju, M., Ding, C., Ren, W., Yang, Y., Zhang, D., & Guo, Y. J. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3050643 · Cited by 225
“Therefore, four commonly used metrics, i.e., the mean of the gradients at the visible edges (R) [56], fog aware density evaluator (FADE) [10], and the aforementioned NIQE [54] and PSNR, are employed to facilitate a quantitative comparison.”
MethodVQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder
Gu, Y., Wang, X., Xie, L., Dong, C., Li, G., Shan, Y., & Cheng, M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19797-0_8 · Cited by 225
Teaching Large Language Models to Regress Accurate Image Quality Scores Using Score Distribution
You, Z., Cai, X. C., Gu, J., Xue, T., & Dong, 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/cvpr52734.2025.01350 · Cited by 225
“Image Quality Assessment (IQA) focuses on perceiving the visual quality of images [26, 41, 66, 84], and is widely adopted in various application scenarios, e.g. , image com-(cid:7)(cid:9)(cid:9)(cid:4) Figure 1.”
SER-FIQ: Unsupervised Estimation of Face Image Quality Based on Stochastic Embedding Robustness
Terhorst, P., Kolf, J. N., Damer, N., Kirchbuchner, F., & Kuijper, A. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00569 · Cited by 221
Structure and Illumination Constrained GAN for Medical Image Enhancement
Ma, Y., Liu, J., Liu, Y., Fu, H., Hu, Y., Cheng, J., Qi, H., Wu, Y., Zhang, J., & Zhao, Y. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3101937 · Cited by 220
“For quantitative evaluation, we adopted three no-reference image quality assessment metrics: Natural Image Quality Evaluator (NIQE) [39], Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) [40] and Perception based Image Quality Evaluator (PIQE) [41].”
MethodPerceptual video quality assessment: a survey
Min, X., Duan, H., Sun, W., Zhu, Y., & Zhai, G. (2024) · Science China Information Sciences · doi:10.1007/s11432-024-4133-3 · Cited by 218
Adapt or Perish: Adaptive Sparse Transformer with Attentive Feature Refinement for Image Restoration
Zhou, S., Chen, D., Pan, J., Shi, J., & Yang, J. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00285 · Cited by 216
“Ad-ditionally, NIQE [52] is used as a non-reference metric.”
MethodWu, H., Zhang, E., Liao, L., Chen, C., Hou, J., Wang, A., Sun, W., Yan, Q., & Lin, W. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01843 · Cited by 215
“Methods Training on SROCC↑ PLCC↑ KROCC↑ NIQE (2013) [11] None 0.”
BackgroundUnderwater Ranker: Learn Which Is Better and How to Be Better
Guo, C., Wu, R., Jin, X., Han, L., Zhang, W., Chai, Z., & Li, C. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i1.25147 · Cited by 215
Underwater Camera: Improving Visual Perception Via Adaptive Dark Pixel Prior and Color Correction
Zhou, J., Liu, Q., Jiang, Q., Ren, W., Lam, K.-M., & Zhang, W. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-023-01853-3 · Cited by 215
“Evaluation Metrics To assess the image quality, we employed four metrics: Underwater Color Image Quality Evaluation (UCIQE) (Yang & Sowmya, 2015), Contrast-changed Image Quality Measure (CEIQ) Yan et al. (2019), Naturalness Image Quality Evaluator (NIQE) (Mittal et al., 2012), and Information Entropy (IE) (Zhang et al…”
InfluentialRAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content
Tu, Z., Yu, X., Wang, Y., Birkbeck, N., Adsumilli, B., & Bovik, A. C. (2021) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2021.3090333 · Cited by 215
“Since ‘completely blind’ models such as NIQE [33] and VIIDEO [47] were not observed to perform reasonably well on these natural video datasets [6], we did not include them.”
BackgroundMethodSelf-citationAutomatic Prediction of Perceptual Image and Video Quality
Bovik, A. C. (2013) · Proceedings of the IEEE · doi:10.1109/jproc.2013.2257632 · Cited by 214
“blind’’ natural image quality evaluator (NIQE) model is thus really a measure of ‘‘image naturalness’’ [140].”
Self-citationLearning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement
Wu, Y., Pan, C., Wang, G., Yang, Y., Wei, J., Li, C., & Shen, H. T. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00166 · Cited by 210
Qi, P., Bu, Y., Cao, J., Ma, W. J., Shui, R., Xiao, J., Wang, D., & Chua, T. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i12.26689 · Cited by 210
MC360IQA: A Multi-channel CNN for Blind 360-Degree Image Quality Assessment
Sun, W., Min, X., Zhai, G., Gu, K., Duan, H., & Ma, S. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2019.2955024 · Cited by 208
“For example, NSS-based models include distortion identification-based image verify and integrity evaluation (DIIVINE) [20], natural image quality evaluator (NIQE) [21], pesudo reference image based measures BPRI [22] and BMPRI [23] etc.”
InfluentialAll-in-One Weather-Degraded Image Restoration Via Adaptive Degradation-Aware Self-Prompting Model
Wen, Y., Gao, T., Li, Z., Zhang, J., Zhang, K., & Chen, T. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3535316 · Cited by 207
“Meanwhile, we employ the naturalness image quality evaluator (NIQE) [46] to quantitatively evaluate the naturalness, where the better perceptual image quality corresponds to lower indicator.”
High-Fidelity Generative Image Compression
Mentzer, F., Toderici, G. D., Tschannen, M., & Agustsson, E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.09965 · Cited by 206
“We find that in the non-conditional setting, SpectralNorm reduces the variability of FID and KID significantly, and, to a lesser extent, also that of LPIPS and NIQE.”
MethodResultInfluentialCross-Modal Transformers for Infrared and Visible Image Fusion
Park, S., Vien, A. G., & Lee, C. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3289170 · Cited by 206
“…for discrete cosine features (FMI dct ) [71] and wavelet features (FMI w ) [71], multiscale structural similarity (MS-SSIM) [72], sum of the correlations of differences (SCD) [73], blind/referenceless image spatial quality evaluator (BRISQUE) [74], and natural image quality evaluator (NIQE) [75].”
BackgroundOptimizing Multistage Discriminative Dictionaries for Blind Image Quality Assessment
Jiang, Q., Shao, F., Lin, W., Gu, K., Jiang, G., & Sun, H. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2763321 · Cited by 204
“Generally, these methods like [30]–[32] share a similar architecture.”
MethodUnpaired Deep Image Deraining Using Dual Contrastive Learning
Chen, X., Pan, J., Jiang, K., Li, Y., Huang, Y., Kong, C., Dai, L., & Fan, Z. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.00206 · Cited by 203
Mixed 2D/3D Convolutional Network for Hyperspectral Image Super-Resolution
Li, Q., Wang, Q., & Li, X. (2020) · Remote Sensing · doi:10.3390/rs12101660 · Cited by 203
“Thus, the universal non-reference hyperspectral image quality evaluation methods (i.e., NIQE [51]) are adopted to evaluate the performance of the reconstruction.”
MethodSingle Image Dehazing Using Saturation Line Prior
Ling, P., Chen, H., Tan, X., Jin, Y., & Chen, E. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3279980 · Cited by 202
“To facilitate an objective comparison in dehazing performance, two widely used non-reference metrics, i.e., the aforementioned FADE and the natural image quality evaluator (NIQE) [52], are adopted to perform the objective evaluation.”
MethodSelective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model
Zheng, D., Wu, X.-M., Yang, S., Zhang, J., Hu, J., & Zheng, W. (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/cvpr52733.2024.02404 · Cited by 202
“The benchmarks are evaluated on peak signal-to-noise ratio (PSNR) [15], structural similarity (SSIM) [59], nat-ural image quality evaluator (NIQE) [35], lightness order error (LOE) [56], integrated local NIQE (IL -NIQE) [72] and learned perceptual image patch similarity (LPIPS) [73] metrics.”
BackgroundLearning temporal coherence via self-supervision for GAN-based video generation
Chu, M., Xie, Y., Mayer, J., Leal-Taixé, L., & Thuerey, N. (2020) · ACM Transactions on Graphics · doi:10.1145/3386569.3392457 · Cited by 201
Depicting Beyond Scores: Advancing Image Quality Assessment Through Multi-modal Language Models
You, Z., Li, Z., Gu, J., Yin, Z., Xue, T., & Dong, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72970-6_15 · Cited by 201
Syn2Real Transfer Learning for Image Deraining Using Gaussian Processes
Yasarla, R., Sindagi, V. A., & Patel, V. M. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00280 · Cited by 200
Deep Learning-based Face Super-resolution: A Survey
Jiang, J., Wang, C., Liu, X., & Ma, J. (2021) · ACM Computing Surveys · doi:10.1145/3485132 · Cited by 201
“Certainly, except PSNR, SSIM, FID, there are still many evaluation metric, such as MS-SSIM, NIQE [119], mean opinion score, and others.”
BackgroundInfluentialESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network
Rakotonirina, N. C., & Rasoanaivo, A. (2020) · ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp40776.2020.9054071 · Cited by 199
“It is based on the Ma’s score [27] and NIQE [28] and equals ((10 − Ma ) + NIQE ) .”
MethodRethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff
Blau, Y., & Michaeli, T. (2019) · arXiv · doi:10.48550/arxiv.1901.07821 · Cited by 198
Wavelength-based Attributed Deep Neural Network for Underwater Image Restoration
Sharma, P., Bisht, I., & Sur, A. (2023) · ACM Transactions on Multimedia Computing, Communications, and Applications · doi:10.1145/3511021 · Cited by 198
“We have incorporated both reference and reference-less image quality metrics for a robust comparison of the proposed scheme, as follows: Mean-Squared Error (MSE), Peak Signalto-Noise Ratio (PSNR), SSIM, Underwater Image Quality Measure (UIQM) [77], Natural Image Quality Evaluator (NIQE) [78], Patch-based Contrast Qual…”
MethodInfluentialLEDNet: Joint Low-Light Enhancement and Deblurring in the Dark
Zhou, S., Li, C., & Change Loy, C. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-20068-7_33 · Cited by 196
SMORE: A Self-Supervised Anti-Aliasing and Super-Resolution Algorithm for MRI Using Deep Learning
Zhao, C., Dewey, B. E., Pham, D. L., Calabresi, P. A., Reich, D. S., & Prince, J. L. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.3037187 · Cited by 196
“We are aware of other open source no-reference perceptual quality metrics such as NIQE [45] and BRISQUE [46], which are designed to correspond to human perception.”
BackgroundWang, X., Yi, J., Guo, J., Song, Y., Lyu, J., Xu, J., Yan, W., Zhao, J., Cai, Q., & Min, H. (2022) · Remote Sensing · doi:10.3390/rs14215423 · Cited by 196
Text-IF: Leveraging Semantic Text Guidance for Degradation-Aware and Interactive Image Fusion
Yi, X., Xu, H., Zhang, H., Tang, L., & Ma, J. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.02552 · Cited by 195
“Metrics include the sum of the correlations of differences (SCD) [2], standard deviation (SD), information entropy (EN) [18], visual information fidelity (VIF) [6], quality of gradient-based fusion ( Q AB/F ) [18], CLIP-IQA [32], NIQE [22], MUSIQ [10], BRISQUE [21], and spatial frequency (SF) [4].”
BackgroundBlind Image Quality Assessment Using Statistical Structural and Luminance Features
Li, Q., Lin, W., Xu, J., & Fang, Y. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2601028 · Cited by 195
“A combination of free energy principle based features and spatial NSS features has shown some impressive results in [33].”
BackgroundMethodInfluentialOneRestore: A Universal Restoration Framework for Composite Degradation
Guo, Y., Gao, Y., Lu, Y., Zhu, H., Liu, R. W., & He, S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72655-2_15 · Cited by 193
No-Reference Quality Assessment for 3D Colored Point Cloud and Mesh Models
Zhang, Z., Sun, W., Min, X., Wang, T., Lu, W., & Zhai, G. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3186894 · Cited by 190
“The 2DNSS features are extracted by the 2D views of objects using BRISQUE [36] and NIQE [51] (The redundant features of BRISQUE and NIQE are removed ).”
MethodRain-Free and Residue Hand-in-Hand: A Progressive Coupled Network for Real-Time Image Deraining
Jiang, K., Wang, Z., Yi, P., Chen, C., Wang, Z., Wang, X., Jiang, J., & Lin, C.-W. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3102504 · Cited by 190
Sun, W., Min, X., Tu, D., Ma, S., & Zhai, G. (2023) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2023.3270621 · Cited by 189
“3) Comparing Algorithms: We compare the proposed models with the state-of-the-art BIQA models, including: (cid:2) Handcrafted feature based BIQA models: QAC [56], NIQE [57], ILNIQE [58], BRISQUE [7], and BMPRI [10].”
MethodStudy of Temporal Effects on Subjective Video Quality of Experience
Bampis, C. G., Li, Z., Moorthy, A. K., Katsavounidis, I., Aaron, A., & Bovik, A. C. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2729891 · Cited by 188
Self-citationBlind Image Super-Resolution: A Survey and Beyond
Liu, A., Liu, Y., Gu, J., Qiao, Y., & Dong, C. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3203009 · Cited by 187
“, NIQE [73]) using reinforcement learning.”
End-to-End Blind Image Quality Prediction With Cascaded Deep Neural Network
Wu, J., Ma, J., Liang, F., Dong, W., Shi, G., & Lin, W. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3002478 · Cited by 187
“NIQE [28] constructs quality aware features and matches them to the multivariate Gaussian (MVG) model.”
Rank-One Prior: Real-Time Scene Recovery
Liu, J., Liu, R. W., Sun, J., & Zeng, T. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3226276 · Cited by 186
“We evaluate the performance of ROP and ROP þ by using two well-known non-reference indexes NIQE (Natural Image Quality Evaluator [15]) and PIQE (Perception-based Image Quality Evaluator [16]) on the collected dataset including Real Underwater, Sand dust, and Hazy images (RUSH).”
MethodGraphIQA: Learning Distortion Graph Representations for Blind Image Quality Assessment
Sun, S., Yu, T., Xu, J., Zhou, W., & Chen, Z. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3152942 · Cited by 185
“statistical properties of natural scene images [30]–[32], [35], [44]–[46].”
BackgroundMultiscale Structure Guided Diffusion for Image Deblurring
Ren, M., Delbracio, M., Talebi, H., Gerig, G., & Milanfar, P. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00984 · Cited by 186
“For benchmarking, we mainly consider perceptual quality of the re-sults quantified by standard metrics for generative models including LPIPS [94], NIQE [49], FID (Fr´echet Inception Distance) [17], and KID (Kernel Inception Distance) [3].”
MethodA survey on image enhancement for Low-light images
Guo, J., Ma, J., García‐Fernández, Á. F., Zhang, Y., & Liang, H. (2023) · Heliyon · doi:10.1016/j.heliyon.2023.e14558 · Cited by 184
Precise No-Reference Image Quality Evaluation Based on Distortion Identification
Yan, C., Teng, T., Liu, Y., Zhang, Y., Wang, H., & Ji, X. (2021) · ACM Transactions on Multimedia Computing, Communications, and Applications · doi:10.1145/3468872 · Cited by 183
“We compare our proposed DIQM with 10 mainstream NR IQA methods, which are LPSI [66], QAC [67], BRISQUE [33], NFERM [18], NIQE [35], IL-NIQE [68], SNP-NIQE [20], BIQI [19], DIIVINE [22], and MEON [23].”
MethodNo-Reference Quality Assessment of Tone-Mapped HDR Pictures
Kundu, D., Ghadiyaram, D., Bovik, A. C., & Evans, B. L. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2685941 · Cited by 182
“using a Generalized Gaussian Distribution (GGD) when used for image quality assessment [18], [19].”
InfluentialSelf-citationEncoder-Free Multiaxis Physics-Aware Fusion Network for Remote Sensing Image Dehazing
Wen, Y., Gao, T., Zhang, J., Li, Z., & Chen, T. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3325927 · Cited by 182
“To gauge the effectiveness of the approaches in real-world unsupervised remote sensing image dehazing, we have employed the subsequent metrics: naturalness image quality evaluator (NIQE) [57] and integrated local NIQE (IL-NIQE) [58].”
MethodA survey of deep learning approaches to image restoration
Su, J., Xu, B., & Yin, H. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.02.046 · Cited by 181
Two-Stream Convolutional Networks for Blind Image Quality Assessment
Yan, Q., Gong, D., & Zhang, Y. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2883741 · Cited by 181
“images [13]–[17], based on some empirical observations that some certain features are distinguishable from the distortionfree images.”
BackgroundMethodExploring Rich Subjective Quality Information for Image Quality Assessment in the Wild
Min, X., Gao, Y., Cao, Y., Zhai, G., Zhang, W., Sun, H., & Chen, C. W. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3544659 · Cited by 181
“The images in these databases have relatively simple distortions, allowing most NR IQA methods to achieve good performance on synthetic distortion databases [25], [26], [27].”
AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment
Li, C., Zhang, Z., Wu, H., Sun, W., Min, X., Liu, X., Zhai, G., & Lin, W. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3319020 · Cited by 180
“II-A reviewed: ● Handcrafted-based models: This group includes four mainstream perceptual quality metrics, namely CEIQ [51], DSIQA [52], NIQE [53], and Sisblim [43].”
Method
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.