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 201–300 of 1,013
Progressive Semantic-Aware Style Transformation for Blind Face Restoration
Chen, C., Li, X., Yang, L., Lin, X., Zhang, L., & Wong, K.-Y. K. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01172 · Cited by 180
“Compared with other no reference metrics such as NIQE [25] and IS (Inception Score) [29] which focus on natural images, FID utilizes a reference HQ face dataset and gives better measurement.”
BackgroundDifFace: Blind Face Restoration With Diffused Error Contraction
Yue, Z., & Loy, C. C. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3432651 · Cited by 179
“In addition, we did investigate several non-reference metrics, including NIQE [62], NRQM [63], and PI [64].”
MethodSyncTalk: The Devil is in the Synchronization for Talking Head Synthesis
Peng, Z., Hu, W., Shi, Y., Zhu, X., Zhang, X., Zhao, H., He, J., Liu, H., & Fan, Z. (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/cvpr52733.2024.00070 · Cited by 180
“For more precise output definition and comparison, we use two No Reference methods: the Natural Image Quality Evaluator (NIQE)[29] and the Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE)[28].”
MethodSelf-supervised Image Enhancement Network: Training with Low Light Images OnlyPreprint
Zhang, Y., Di, X., Zhang, B., & Wang, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.11300 · Cited by 180
“In this paper, we use gray entropy (GE), color entropy (CE, color entropy is the sum of entropy of R,G,B channels), gray mean illumination (GMI), gray mean gradient (GMG), LOE [23], NIQE [46], PSNR, SSIM to evaluate the enhanced image.”
MethodQoE Modeling for HTTP Adaptive Video Streaming–A Survey and Open Challenges
Barman, N., & Martini, M. G. (2019) · IEEE Access · doi:10.1109/access.2019.2901778 · Cited by 178
“The authors evaluate 6 objective IQA metrics (PSNR, PSNRHVS [95], SSIM, MS-SSIM [96], NIQE [43] and GMSD [97]) and two VQA metrics (VMAF [98] and STRRED [89]) on the subjective dataset and it is observed that STRRED gives the highest performance in terms of SROCC considering both a subset of the…”
MethodSemantically Contrastive Learning for Low-Light Image Enhancement
Liang, D., Li, L., Wei, M., Yang, S., Zhang, L., Yang, W., Du, Y., & Zhou, H. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20046 · Cited by 178
Light Field Image Super-Resolution Using Deformable Convolution
Wang, Y., Yang, J., Wang, L., Ying, X., Wu, T., An, W., & Guo, Y. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3042059 · Cited by 177
“As shown in Table I, our NUDT dataset achieves the best scores in BRISQUE, CEIQ, and ENIQA, and achieves the second best scores in NIQE and NRLFQA.”
BackgroundInfluentialAutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion
Jiang, Y., Zhang, Z., Xue, T., & Gu, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73661-2_19 · Cited by 177
Fourier Space Losses for Efficient Perceptual Image Super-Resolution
Fuoli, D., Van Gool, L., & Timofte, R. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00236 · Cited by 176
“RankSRGAN [37] introduces a method to use non-differentiable handcrafted image quality metrics (Ma [25], NIQE [26] and PI [2]) for training in a GAN-based setup.”
MethodInfluentialCID2013: A Database for Evaluating No-Reference Image Quality Assessment Algorithms
Virtanen, T., Nuutinen, M., Vaahteranoksa, M., Oittinen, P., & Hakkinen, J. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2378061 · Cited by 176
“Conventionally, NR measures are based on the assumption that a specific and known distortion type has distorted the image [14]–[17].”
BackgroundMethodIntegrating Semantic Segmentation and Retinex Model for Low-Light Image Enhancement
Fan, M., Wang, W., Yang, W., & Liu, J. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413757 · Cited by 176
“As there is no normal-light ground truth in our real-captured data, we only use the no-reference metric NIQE [29].”
MethodUnified Quality Assessment of in-the-Wild Videos with Mixed Datasets Training
Li, D., Jiang, T., & Jiang, M. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01408-w · Cited by 175
CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability
Boutros, F., Fang, M., Klemt, M., Fu, B., & Damer, N. (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/cvpr52729.2023.00565 · Cited by 174
Spatial-Frequency Mutual Learning for Face Super-Resolution
Wang, C., Jiang, J., Zhong, Z., & Liu, X. (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/cvpr52729.2023.02141 · Cited by 174
“In terms of evaluation metrics, PSNR, SSIM [44], LPIPS [56] and NIQE [35] results are used.”
MethodA comprehensive review of deep learning-based single image super-resolution
Bashir, S. M. A., Wang, Y., Khan, M., & Niu, Y. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.621 · Cited by 172
RetractedBlindly Assess Quality of In-the-Wild Videos via Quality-Aware Pre-Training and Motion Perception
Li, B., Zhang, W., Tian, M., Zhai, G., & Wang, X. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3164467 · Cited by 171
“The representative BIQA models are NIQE [25], IL-NIQE [67], BRISQUE [8], M3 [68], HIGRADE [69], FRIQUEE [26], CORNIA [30], HOSA [70], and pre-trained DNN models, VGG-19 [71], ResNet-50 [50].”
BackgroundMethodInfluentialHiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment
Yang, L., Wang, S., Ma, S., Gao, W., Liu, C., Wang, P., & Ren, P. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413965 · Cited by 171
Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network
Lao, S., Gong, Y., Shi, S., Yang, S., Wu, T., Wang, J., Xia, W., & Yang, Y. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00123 · Cited by 171
Cao, J., Wang, Q., Xian, Y., Li, Y., Ni, B., Pi, Z., Zhang, K., Zhang, Y., Timofte, R., & Gool, L. V. (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/cvpr52729.2023.00179 · Cited by 172
“Methods Scales NIQE ↓ [58] BRISQUE ↓ [57] PIQE ↓ [73]”
BackgroundFourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring
Lv, X., Zhang, S., Wang, C., Zheng, Y., Zhong, B., Li, C., & Nie, L. (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/cvpr52733.2024.02398 · Cited by 171
“…we use four commonly-used no-reference image quality metrics to perform quantitative comparisons, including Natural Image Quality Evaluator (NIQE) [44], Perceptual Index (PI) [1], Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) [43], and Multi-Scale Image Quality Transformer (MUSIQ)…”
MethodAi, Y., Huang, H., Zhou, X., Wang, J., & He, R. (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/cvpr52733.2024.02403 · Cited by 171
Face Image Quality Assessment: A Literature Survey
Schlett, T., Rathgeb, C., Henniger, O., Galbally, J., Fierrez, J., & Busch, C. (2022) · ACM Computing Surveys · doi:10.1145/3507901 · Cited by 170
“FaceNet [119] and ArcFace [123] for FR, and selected images using QSs from both SER-FIQ variants, FaceQnet v0 [50], an approach proposed by Best-Rowden in [109], 3 general IQAAs (BRISQUE [113], NIQE [124], PIQE [125]), as well as a COTS (Neurotec Biometric SDK 11.1 [111]). The SER-FIQ “on-top model” was noted to mostl…”
MethodInfluentialDepth Information Assisted Collaborative Mutual Promotion Network for Single Image Dehazing
Zhang, Y., Zhou, S., & Li, H. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00275 · Cited by 169
“Evaluation Metrics.”
A highly efficient method for blind image quality assessment
Wu, Q., Wang, Z., & Li, H. (2015) · 2015 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2015.7350816 · Cited by 145
“Both the OA-BIQA (BIQI [2], BLINDS-II [5], BRISQUE [6] and CORNIA [7]) and OF-BIQA (NIQE [13]) metrics are included in this comparison.”
BackgroundPerceptual Image Quality Assessment with Transformers
Cheon, M., Yoon, S.-J., Kang, B., & Lee, J. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00054 · Cited by 168
“In general, the objective IQA methods can be classified into three categories according to the existence of reference information: FR [51, 52, 40, 32, 5], reduced-reference (RR) [43], and noreference (NR) [36, 35] IQA methods.”
LightingNet: An Integrated Learning Method for Low-Light Image Enhancement
Yang, S., Zhou, D., Cao, J., & Guo, Y. (2023) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2023.3240087 · Cited by 168
“…four No-reference evaluation criteria to compare our model with other low-light enhancement methods, including METAIQA [67], BRISQUE [69], NIQE [70], PIQE [68], as shown in Table II, the proposed LightingNet outperformed most of the comparison methods in terms of BRISQUE and METAIQA…”
Efficient Diffusion Model for Image Restoration by Residual Shifting
Yue, Z., Wang, J., & Loy, C. C. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3461721 · Cited by 170
NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results
Lugmayr, A., Danelljan, M., Timofte, R., Ahn, N., Bai, D., Cai, J., Cao, Y., Chen, J., Cheng, K., Chun, S., et al. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00255 · Cited by 167
“The team furthermore use an LR-conditional frequency-separation discriminator to train the model and employ AutoML to tune the loss weights, employing LPIPS [76] and NIQE [52] as objective.”
MethodInfluentialBlind omnidirectional image quality assessment with viewport oriented graph convolutional networks
Xu, J., Zhou, W., & Chen, Z. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3015186 · Cited by 166
“purpose NR IQA has been proposed to handle different distortion types and levels [21], [28]–[34].”
BackgroundRecent advances in image dehazing
Wang, W., & Yuan, X. (2017) · IEEE/CAA Journal of Automatica Sinica · doi:10.1109/jas.2017.7510532 · Cited by 166
“Ma et al. [215] adopted eight dehazing algorithms to perform image dehazing on 25 images, then evaluated the quality through subjective users and some general IQA methods (BIQI [216], BRISQUE [217], NIQE [218], BLINDS-II [219], DILT [220] and NCDQI [221]) and concluded that none of these IQA models properly predicts t…”
MethodQuality of Experience for Streaming Services: Measurements, Challenges and Insights
Bouraqia, K., Sabir, E., Sadik, M., & Ladid, L. (2020) · IEEE Access · doi:10.1109/access.2020.2965099 · Cited by 167
“approaches are Peak Signal toNoise Ratio (PSNR), Structural Similarity Metric (SSIM) [33], Multi-Scale Structural SiMilarity [34], SSIMplus [35](supports cross frame rate and cross resolution), Video Quality Model (VQM) [36], and Natural Image Quality Evaluator (NIQE) [37].”
MethodUDAformer: Underwater image enhancement based on dual attention transformer
Shen, Z., Xu, H., Luo, T., Song, Y., & He, Z. (2023) · Computers & Graphics · doi:10.1016/j.cag.2023.01.009 · Cited by 166
A Perceptual Quality Assessment Exploration for AIGC Images
Zhang, Z., Li, C., Sun, W., Liu, X., Min, X., & Zhai, G. (2023) · IEEE International Conference on Multimedia and Expo workshops · doi:10.1109/icmew59549.2023.00082 · Cited by 166
“…as technical issues, AI artifacts, unnaturalness, discrepancy, and [18] 0.2948 0.2746 0.3143 0.2873 DSIQA [19] -0.3282 -0.0741 -0.3372 -0.0857 NIQE [20] -0.5256 -0.4901 -0.5853 -0.5423 SISBLIM [21] -0.3133 -0.4331 -0.0135 -0.3009 &SVR-based friquee [22] 0.4654 0.3752 0.5165 0.4153 GMLF [23] 0.5200…”
MethodInfluentialComputer-aided diagnosis of cataract using deep transfer learning
Pratap, T., & Kokil, P. (2019) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2019.04.010 · Cited by 165
NightHazeFormer: Single Nighttime Haze Removal Using Prior Query Transformer
Liu, Y., Yan, Z., Chen, S., Tian, Y., Ren, W., & Chen, E. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3611744 · Cited by 165
“Moreover, it achieves the best MUSIQ-AVA and NIQE scores on the REAL-NH test dataset, verifying its outstanding generalization performance.”
MethodElmezain, M., Saoud, L. S., Sultan, A., Heshmat, M., Seneviratne, L. D., & Hussain, I. (2025) · IEEE Access · doi:10.1109/access.2025.3534098 · Cited by 165
“Natural Image Quality Evaluator (NIQE): NIQE [31] indicates the naturalness of an image by measuring its statistical deviation from the natural scene statistics, where a lower color indicates a more natural-looking image.”
Structure-Preserving Deraining with Residue Channel Prior Guidance
Yi, Q., Li, J., Dai, Q., Fang, F., Zhang, G., & Zeng, T. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00420 · Cited by 164
Blind Image Quality Assessment Based on Multichannel Feature Fusion and Label Transfer
Wu, Q., Li, H., Meng, F., Ngan, K. N., Luo, B., Huang, C., & Zeng, B. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2412773 · Cited by 164
“, the BLINDS-II [15] focuses on the DCT domain, the DIIVINE [16] works on the wavelet domain and the NIQE [17] is executed on the spatial domain.”
BackgroundMethodInfluentialLearning to Rank for Blind Image Quality Assessment
Gao, F., Tao, D., Gao, X., & Li, X. (2015) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2014.2377181 · Cited by 163
“Although there have been several BIQA methods that do not require learning from subjectively eval uated images [23]-[25], their performance is still inferior to state-of-the-art algorithms.”
MethodLuminance-Aware Pyramid Network for Low-Light Image Enhancement
Li, J., Li, J., Fang, F., Li, F., & Zhang, G. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.3021243 · Cited by 162
An Introduction to Neural Data Compression
Yang, Y., Mandt, S., & Theis, L. (2023) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1561/0600000107 · Cited by 165
Quality-aware Pretrained Models for Blind Image Quality Assessment
Zhao, K., Yuan, K., Sun, M. B., Li, M., & Wen, X. (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/cvpr52729.2023.02136 · Cited by 163
Xiao, Y., Su, X., Yuan, Q., Liu, D., Shen, H., & Zhang, L. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3107352 · Cited by 160
“1) Quantitative Evaluation: We adopt PSNR, SSIM, RMSE, CC, and NIQE [63] as the evaluation metrics.”
MethodGe, X., Ding, J., Jin, X., Wang, J., Chen, X., Li, X., Liu, J., & Xie, B. (2021) · Remote Sensing · doi:10.3390/rs13081562 · Cited by 160
Acharya, U. K., & Kumar, S. (2021) · Optik · doi:10.1016/j.ijleo.2021.166273 · Cited by 160
Zhou, W., Yu, L., Zhou, Y., Qiu, W., Wu, M.-W., & Luo, T. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2794207 · Cited by 159
“[21] presented the NSI quality evaluator (NIQE), which does not require training with humanscored distorted NSIs.”
BackgroundMethodInfluentialCoupled Adversarial Training for Remote Sensing Image Super-Resolution
Lei, S., Shi, Z., & Zou, Z. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2959020 · Cited by 159
“Here, we use two non-reference image quality metrics, i.e., NIQE [53] and SSEQ [54], to assess these super-resolved results.”
MethodMedical image fusion using multi-level local extrema
Xu, Z. (2013) · Information Fusion · doi:10.1016/j.inffus.2013.01.001 · Cited by 158
“[46] put forward a kind of blind image quality analysis model named Natural Image Quality Evaluator (NIQE) to evaluate image quality without knowledge of distortions or human opinions in advance.”
Space-Time-Aware Multi-Resolution Video Enhancement
Haris, M., Shakhnarovich, G., & Ukita, N. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00293 · Cited by 158
“I t I sr t+ Loss PSNR SSIM NIQE [38] PSNR SSIM NIQE [38] Lf 32.”
BackgroundNo-Reference Quality Assessment of Contrast-Distorted Images using Contrast EnhancementPreprint
Yan, J., Li, J., & Fu, X. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.08879 · Cited by 158
“stics (NSS) based features constitute the majority of existing NR-IQA methods. A plethora of NSS models in different spatial or transform domains have been incorporated into state -of-the-art methods [3, 4, 5, 6, 7, 8, 9, 10, 11, 12]. In [ 12], a bag of feature maps over several transform domains and three color space…”
MethodModel-Based Referenceless Quality Metric of 3D Synthesized Images Using Local Image Description
Gu, K., Jakhetiya, V., Qiao, J., Li, X., Lin, W., & Thalmann, D. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2733164 · Cited by 157
“Besides these, the Natural Image Quality Evaluator (NIQE) [16] and Integrated Local NIQE (IL-NIQE) [17], which are free of learning and human scored images, have aroused more attention.”
BackgroundInfluentialPolarimetric image recovery method combining histogram stretching for underwater imaging
Li, X., Hu, H., Zhao, L., Wang, H., Yu, Y., Wu, L., & Liu, T. (2018) · Scientific Reports · doi:10.1038/s41598-018-30566-8 · Cited by 157
Natural and Realistic Single Image Super-Resolution With Explicit Natural Manifold Discrimination
Soh, J. W., Park, G. Y., Jo, J., & Cho, N. I. (2019) · 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.2019.00831 · Cited by 156
“We assess the methods with the NR-IQAs and the results are summarized in Figure 8, which shows the average NIQE and NQSR tested with BSD100.”
BackgroundMethodInfluentialLiu, Y., Gu, K., Zhang, Y., Li, X., Zhai, G., Zhao, D., & Gao, W. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2900472 · Cited by 157
“As suggested in [7] and [9], the distribution of the MSCN coefficients is modeled through the zero-mean GGD and the obtained distribution parameters are employed as the features to indicate the naturalness degree.”
MethodInfluentialMM-PCQA: Multi-Modal Learning for No-reference Point Cloud Quality Assessment
Zhang, Z., Sun, W., Min, X., Wang, Q., He, J. H., Zhou, Q. F., & Zhai, G. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/195 · Cited by 155
In-Capture Mobile Video Distortions: A Study of Subjective Behavior and Objective Algorithms
Ghadiyaram, D., Pan, J., Bovik, A. C., Moorthy, A. K., Panda, P., & Yang, K.-C. (2018) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2707479 · Cited by 154
“Many of the natural scene statistics-based models performed quite well on videos in the artifacts category, which agrees with previous work that showed that NSS-based features effectively predict the impacts of noise, blockiness, and blur on perceived quality [15], [37], [39].”
MethodSelf-citationNatural-based underwater image color enhancement through fusion of swarm-intelligence algorithm
Azmi, K. Z. M., Ghani, A. S. A., Yusof, Z. M., & Ibrahim, Z. (2019) · Applied Soft Computing · doi:10.1016/j.asoc.2019.105810 · Cited by 155
Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
Liang, J., Lugmayr, A., Zhang, K., Danelljan, M., Gool, L. V., & Timofte, R. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00404 · Cited by 154
Rich features for perceptual quality assessment of UGC videos
Wang, Y., Ke, J., Talebi, H., Yim, J. G., Birkbeck, N., Adsumilli, B., Milanfar, P., & Yang, F. (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/cvpr46437.2021.01323 · Cited by 153
“Since traditional no-reference metrics [18, 20, 19, 34, 5] mainly rely on several manually designed features that are summarized from limited samples, they don’t perform well on various UGC conditions.”
BackgroundMethodImage dehazing using polarization effects of objects and airlight
Fang, S., Xia, X., Huo, X., & Chen, C. W. (2014) · Optics Express · doi:10.1364/oe.22.019523 · Cited by 151
Perceptual evaluation of single image dehazing algorithms
Ma, K., Liu, W., & Wang, Z. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351475 · Cited by 151
“General purpose no-reference IQA models [30, 31, 32, 33, 34] and no-reference models for contrast-distorted images [35] may be applicable but are never tested on dehazed images.”
BackgroundMethodSpEED-QA: Spatial Efficient Entropic Differencing for Image and Video Quality
Bampis, C. G., Gupta, P., Soundararajan, R., & Bovik, A. C. (2017) · IEEE Signal Processing Letters · doi:10.1109/lsp.2017.2726542 · Cited by 150
“These ideas are effectively modeled in the spatial domain using simple filters [23] in NR algorithms such as BRISQUE [8] and NIQE [26] to achieve high quality prediction performance with very low computational complexity.”
MethodSelf-citationA Comprehensive Performance Evaluation of Image Quality Assessment Algorithms
Athar, S., & Wang, Z. (2019) · IEEE Access · doi:10.1109/access.2019.2943319 · Cited by 151
“Like BRISQUE [130] (discussed in the previous sub-section), NIQE operates at two scales in the spatial domain by converting an image into MSCN coefficients, uses the GGD to fit the empirical distribution of these coefficients, uses the AGGD to fit the empirical distribution of pairwise coefficient products, and uses t…”
BackgroundMethodInfluentialShadow Removal by a Lightness-Guided Network With Training on Unpaired Data
Liu, Z., Yin, H., Mi, Y., Pu, M., & Wang, S. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3048677 · Cited by 150
“Specifically, we adopt the broadly used SSEQ [58], NIQE [59], and DBCNN [60] as blind image quality assessment metrics and compute each metric on each shadow removal result and then average the scores over all the results.”
Multiscale Low-Light Image Enhancement Network With Illumination Constraint
Fan, G., Fan, B., Gan, M., Chen, G., & Chen, C. L. P. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3186880 · Cited by 150
“For non-referenced evaluation indicators, we use NIQE [58] as a quantitative evaluation indicator.”
MethodNo-reference color image quality assessment: from entropy to perceptual quality
Chen, X., Zhang, Q., Lin, M., Yang, G., & He, C. (2019) · EURASIP Journal on Image and Video Processing · doi:10.1186/s13640-019-0479-7 · Cited by 149
No-Reference and Robust Image Sharpness Evaluation Based on Multiscale Spatial and Spectral Features
Li, L., Xia, W., Lin, W., Fang, Y., & Wang, S. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2640762 · Cited by 148
“Database Criterion BIQI [45] BLIINDS-II [46] BRISQUE [47] DIIVINE [48] SSEQ [49] NIQE [50] QAC [51] RISE”
BackgroundMethodArbitrary-steps Image Super-resolution via Diffusion Inversion
Yue, Z., Liao, K., & Loy, C. 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/cvpr52734.2025.02156 · Cited by 148
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Pan, X., Zhan, X., Dai, B., Lin, D., Loy, C. C., & Luo, P. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58536-5_16 · Cited by 147
Chen, B., Zhu, L., Li, G., Lu, F., Fan, H., & Wang, S. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3088505 · Cited by 147
Efficient Frequency-Domain Image Deraining with Contrastive Regularization
Gao, N., Jiang, X., Zhang, X., & Deng, Y. C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72940-9_14 · Cited by 147
Unsupervised Decomposition and Correction Network for Low-Light Image Enhancement
Jiang, Q., Mao, Y., Cong, R., Ren, W., Huang, C., & Shao, F. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3165176 · Cited by 146
“2) Evaluation Metrics: For all datasets, the Natural Image Quality Evaluator NIQE [51] metric is adopted to evaluate the performance of LIE methods.”
MethodZhou, M., Shen, W., Wei, X., Luo, J., Jia, F., Zhuang, X., & Jia, W. (2025) · International Journal of Computer Vision · doi:10.1007/s11263-024-02338-7 · Cited by 146
“…optimization process of a specific method, and from top to bottom, the methods include blind/referenceless image spatial quality evaluator (BRISQUE) (Mittal et al., 2012a), patches to pictures (PaQ2PiQ) (Ying et al., 2020), and the method which is based on transformers, relative ranking, and self…”
InfluentialGreen learning: Introduction, examples and outlook
Kuo, C. ‐. J., & Madni, A. M. (2022) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2022.103685 · Cited by 147
Neighbourhood Representative Sampling for Efficient End-to-End Video Quality Assessment
Wu, H., Chen, C., Liao, L., Hou, J., Sun, W., Yan, Q., Gu, J., & Lin, W. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3319332 · Cited by 145
“Classical VQA Methods: Classical VQA methods [31], [32], [33], [34] employ handcraft features to evaluate video quality.”
MethodDreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting
Zhou, S., Fan, Z., Xu, D., Chang, H., Chari, P., Bharadwaj, T., You, S. O., Wang, Z., & Kadambi, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72658-3_19 · Cited by 146
Highly Efficient Picture-Based Prediction of PM2.5 Concentration
Gu, K., Qiao, J., & Li, X. (2018) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2018.2840515 · Cited by 144
Q-Insight: Understanding Image Quality via Visual Reinforcement Learning
Li, W., Zhang, X., Zhao, S., Zhang, Y., Li, J., Zhang, L., & Zhang, J. (2025) · neural information processing systems · doi:10.52202/085713-1237 · Cited by 144
A Novel Retinex-Based Fractional-Order Variational Model for Images With Severely Low Light
Gu, Z., Li, F., Fang, F., & Zhang, G. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2958144 · Cited by 143
“12(a), we can find that NIQE value is the inverse ratio to β, and for the same β, changes of α have few impacts on it.”
BackgroundInfluentialA Review of GAN-Based Super-Resolution Reconstruction for Optical Remote Sensing Images
Wang, X., Sun, L., Chehri, A., & Song, Y. (2023) · Remote Sensing · doi:10.3390/rs15205062 · Cited by 144
“The natural image quality evaluator (NIQE) [127] is an objective evaluation metric.”
BackgroundGLARE: Low Light Image Enhancement via Generative Latent Feature Based Codebook Retrieval
Zhou, H., Dong, W., Liu, X., Liu, S., Min, X., Zhai, G., & Chen, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73195-2_3 · Cited by 142
Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood ModelsPreprint
Muckley, M. J., El-Nouby, A., Ullrich, K., Jeǵou, H., & Verbeek, J. J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2301.11189 · Cited by 142
“Another class of measures includes no-reference measures such as NIQE (Mittal et al., 2012), FID (Heusel et al., 2017), and KID (Bi´nkowski et al., 2018).”
BackgroundSavi, S., Comiti, F., & Strecker, M. R. (2021) · Earth Surface Processes and Landforms · doi:10.1002/esp.5100 · Cited by 141
“(Mittal et al., 2013), and (ii) the percentage of shadows and fresh snow cover that were present on each image.”
BackgroundMethodSAR-to-optical image translation based on improved CGAN
Yang, X., Zhao, J., Wei, Z., Wang, N., & Gao, X. (2021) · Pattern Recognition · doi:10.1016/j.patcog.2021.108208 · Cited by 142
A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends
Jiang, J., Zuo, Z., Wu, G., Jiang, K., & Liu, X. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3598132 · Cited by 145
“No-reference metrics(e.g., Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
InfluentialContinual Learning for Blind Image Quality Assessment
Zhang, W., Li, D., Ma, C., Zhai, G., Yang, X., & Ma, K. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3178874 · Cited by 140
“We greedily TABLE 5 Performance Comparison of Different BIQA Models Methods mSRCC mPI mSI mPSI NIQE [15] 0.4515 0.4515 1.0000 0.7258 dipIQ [83] 0.3633 0.3633 1.0000 0.6817 Ma19 [34] 0.5664 0.5664 1.0000 0.7832 BRISQUE [4] 0.5235 0.6929 0.6149 0.6539 CORNIA [5] 0.4948 0.6455 0.7069 0.6762 DBCNN [33] 0.6957 0.8814 0.788…”
BackgroundMethodInfluentialRRSGAN: Reference-Based Super-Resolution for Remote Sensing Image
Dong, R., Zhang, L., & Fu, H. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3046045 · Cited by 140
ATMFN: Adaptive-Threshold-Based Multi-Model Fusion Network for Compressed Face Hallucination
Jiang, K., Wang, Z., Yi, P., Wang, G., Gu, K., & Jiang, J. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2960586 · Cited by 139
“…convincing validation, we introduce additional quantitative indicators without reference [67], including Naturalness Image Quality Evaluator (NIQE) [68], Blind Pseudo-reference Image Metric (BPRI) [69], and NR Free Energy-Based Robust Metric (NFERM) [70], to distinguish from pixel-based evaluation…”
MethodLow-light image enhancement based on virtual exposure
Wang, W., Yan, D., Wu, X., He, W., Chen, Z., Yuan, X., & Li, L. (2023) · Signal Processing Image Communication · doi:10.1016/j.image.2023.117016 · Cited by 139
Deep Back-ProjectiNetworks for Single Image Super-Resolution
Haris, M., Shakhnarovich, G., & Ukita, N. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3002836 · Cited by 138
Symmetric Parallax Attention for Stereo Image Super-Resolution
Wang, Y., Ying, X., Wang, L., Yang, J., An, W., & Guo, Y. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00086 · Cited by 138
“Lower scores of BRISQUE [15], NIQE [16] and higher scores of CEIQ [30] indicate better quality.”
BackgroundMethodImage Dehazing Using Residual-Based Deep CNN
Li, J., Li, G., & Fan, H. (2018) · IEEE Access · doi:10.1109/access.2018.2833888 · Cited by 136
Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approach
Sun, L., Wu, R., Ma, Z., Liu, S., Yi, Q., & 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/cvpr52734.2025.00223 · Cited by 136
“…LPIPS [67] and DISTS [9], computed in the RGB space, are used to assess the perceptual quality of SR results; FID [13] evaluates the distance of distributions between GT and restored images; NIQE [33], CLIPIQA [45], MUSIQ [21] and MANIQA [58] evaluate the image quality without reference images.”
Image Sharpness Assessment by Sparse Representation
Li, L.-D., Wu, D., Wu, J.-J., Li, H.-L., Lin, W., & Kot, A. (2016) · IEEE transactions on multimedia · doi:10.1109/tmm.2016.2545398 · Cited by 116
“General-purpose metrics estimate the quality of an image without knowing the distortion types in advance [12]–[15].”
BackgroundMethodMDCN: Multi-Scale Dense Cross Network for Image Super-Resolution
Li, J., Fang, F., Li, J., Mei, K., & Zhang, G. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3027732 · Cited by 134
Li, J., Li, B., Tu, Z., Liu, X., Guo, Q., Juefei-Xu, F., Xu, R., & Yu, H. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01440 · Cited by 134
“For the quantitative assessment on low-light enhancement task, due to lack of paired day-night data in the real autonomous driving scenario, we employ nine no-reference image quality evaluation (IQA) metrics, MUSIQ [24], NIQE [36], Hyper-IQA [47], ILNIQE [54], MANIQA [52], NIMA [48] and TReS [13].”
MethodAdaptive deep learning framework for robust unsupervised underwater image enhancement
Saleh, A., Sheaves, M., Jerry, D., & Azghadi, M. R. (2022) · Expert systems with applications · doi:10.1016/j.eswa.2024.126314 · Cited by 122
“…Measure (UIQM) (Panetta et al., 2016), Multi-scale Image Quality Transformer (MUSIQ) (Ke et al., 2021), and Natural Image Quality Evaluator (NIQE) (Mittal et al., 2013) which are used for unpaired test sets (DeepFish (Saleh et al., 2020), FISHTRAC (Mandel et al., 2023), FishID (LopezMarcano et…”
InfluentialFast curvelet transform through genetic algorithm for multimodal medical image fusion
Arif, M., & Wang, G. (2019) · Soft Computing · doi:10.1007/s00500-019-04011-5 · Cited by 133
Tensor Oriented No-Reference Light Field Image Quality Assessment
Zhou, W., Shi, L., Chen, Z., & Zhang, J. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2969777 · Cited by 133
“PSNR [10] [18] [12] [11] [13] [20] [17] [19] [32] [31] [33] [21] [35] [36] [25] [22] [22] [24] [23] [37] [40] [41]”
Jiang, Q., Liu, Z., Gu, K., Shao, F., Zhang, X., Liu, H., & Lin, W. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3154588 · Cited by 133
“These NR-IQA metrics include GM-LOG [28], BLIINDS-II [29], CurveletQA [30], BRISQUE [31], OG-IQA [32], SSEQ [33], DIIVINE [34], RISE [35], BMPRI [36], FRIQUEE [37], NIQE [38], ILNIQE [39], HVS-MaxPol [40], PCRL [41], and SR-metric [14].”
MethodInfluential
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.