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 801–900 of 1,013
Single image dehazing using extended local dark channel prior
Dwivedi, P., & Chakraborty, S. (2023) · Image and Vision Computing · doi:10.1016/j.imavis.2023.104747 · Cited by 53
Blind Image Quality Assessment: A Fuzzy Neural Network for Opinion Score Distribution Prediction
Gao, Y., Min, X., Zhu, Y., Zhang, X.-P. S., & Zhai, G. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3295375 · Cited by 53
“Meanwhile, we compare the proposed method with several state-of-the-art IQA methods: BRISQUE [19], NIQE [71], BMPRI [16], Kang et al. [21], (Wa)DIQaM-N [22], SGDNet [23], DBCNN [35], HyperIQA [24], UNIQUE [72], DACNN [73], and GraphIQA [74].”
MethodZhou, H., Zhu, X., Zhu, J., Zheng, H., Zhang, S.-X., Qin, J., & Yin, X.-C. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01136 · Cited by 53
“As mentioned in [47, 45], current non-reference metrics (e.g., NIQE [28], NRQM [27], and PI [1]) are not consistent with the perceptual visual system.”
ResultFFTFormer: A spatial-frequency noise aware CNN-Transformer for low light image enhancement
Pei, X., Huang, Y., Su, W., Zhu, F., & Liu, Q. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113055 · Cited by 53
Medical image fusion by combining parallel features on multi-scale local extrema scheme
Du, J., Li, W., Xiao, B., & Nawaz, Q. (2016) · Knowledge-Based Systems · doi:10.1016/j.knosys.2016.09.008 · Cited by 53
Effective and Efficient Blind Quality Evaluator for Contrast Distorted Images
Yue, G., Hou, C., Zhou, T., & Zhang, X. (2018) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2018.2868555 · Cited by 53
“To validate the superiority of the proposed method, we compare it with a number of IQA methods including: 1) classical FR/RR methods (e.g., SSIM [25], FSIM [28], MAD [27], GSIM [29], and RRED [30]) and 2) state-of-the-art NR IQA methods (e.g., NIQE [47], BRISQUE [48], NFERM [49], Fang’s method [36], and NIQMC [38]).”
MethodBlind image quality assessment via learnable attention-based pooling
Gu, J., Meng, G., Xiang, S., & Pan, C. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.02.021 · Cited by 53
Blind Night-Time Image Quality Assessment: Subjective and Objective Approaches
Xiang, T., Yang, Y., & Guo, S. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2938612 · Cited by 53
“Since all the involved methods except NIQE [10] and ILNIQE [11] require a training stage to calibrate regression models, we randomly divide the NNID database into two nonoverlapping sub-sets based on image content, a training set and a test set, such that the image contents of these two sets do not…”
BackgroundMethodLow-Light Image Enhancement via Pair of Complementary Gamma Functions by Fusion
Li, C., Tang, S., Yan, J., & Zhou, T. (2020) · IEEE Access · doi:10.1109/access.2020.3023485 · Cited by 53
“Besides the subjective visual appearance and to further explain the effectiveness of our method, we employ NIQE [36], ILNIQE [37], SSEQ [38], and BRISQUE [42] to objectively evaluate the results of our method.”
MethodForgeryNIR: Deep Face Forgery and Detection in Near-Infrared Scenario
Yukai, W. A. N. G., Peng, C., Liu, D., Wang, N., & Gao, X. (2022) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2022.3146766 · Cited by 53
Perceptual Quality Assessment of Cartoon Images
Chen, H., Chai, X., Shao, F., Wang, X., Jiang, Q., Chao, M., & Ho, Y. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3121875 · Cited by 52
“…nineteen state-of-the-art NR-IQA metrics: eleven metrics designed for natural images (e.g., BPRI [24], BMPRI [25], BIQI [21], BRISQUE [5], NIQE [52], TCLT [22], IL-NIQE [53], OG-IQA [59], SSEQ [36], DBCNN [60], HyperIQA [61]), two metrics for contrast-changed (CC) natural images (e.g., NIQMC…”
BackgroundDCA-CycleGAN: Unsupervised single image dehazing using Dark Channel Attention optimized CycleGAN
Mo, Y., Li, C., Zheng, Y., & Wu, X. (2021) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2021.103431 · Cited by 52
Enhancing resolution of micro-CT images of reservoir rocks using super resolution
Zhao, B., Saxena, N., Hofmann, R., Pradhan, C., & Hows, A. M. (2022) · Computers & Geosciences · doi:10.1016/j.cageo.2022.105265 · Cited by 52
PPformer: Using pixel-wise and patch-wise cross-attention for low-light image enhancement
Dang, J., Zhong, Y., & Qin, X. (2024) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2024.103930 · Cited by 53
Qu, Q., Liang, H., Chen, X., Chung, Y. Y., & Shen, Y. (2024) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2024.3372037 · Cited by 52
“…(FR-IQA) such as PSNR, SSIM [56], MS-SSIM [58], IW-SSIM [57], VIF [44], FSIM [63], GMSD [61], VSI [62], DSS [2], HaarPSI [41], MDSI [33], LPIPS [64], PieAPP [37], and DISTS [9], along with no-reference image quality assessment metrics (NR-IQA) such as BRISQUE [29], NIQE [31], and CLIP-IQA [52].”
MethodLow-light image enhancement using generative adversarial networks
Wang, L., Zhao, L., Zhong, T., & Wu, C. (2024) · Scientific Reports · doi:10.1038/s41598-024-69505-1 · Cited by 52
“For no-reference performance metrics, we used Natural Image Quality Evaluator (NIQE) 41 and Meta Image Quality Assessment (MetaIQA) 42 to assess the quality of enhanced images.”
MethodInfluentialQ-Ground: Image Quality Grounding with Large Multi-modality Models
Chen, C., Yang, S., Wu, H., Liao, L., Zhang, Z., Wang, A., Sun, W., Yan, Q., & Lin, W. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680575 · Cited by 52
MISC: Ultra-Low Bitrate Image Semantic Compression Driven by Large Multimodal Model
Li, C., Lu, G. S., Feng, D., Wu, H., Zhang, Z., Liu, X., Zhai, G., Lin, W., & Zhang, W. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3515874 · Cited by 52
Toward a No-Reference Image Quality Assessment Using Statistics of Perceptual Color Descriptors
Lee, D., & Plataniotis, K. N. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2579308 · Cited by 52
Image Quality Ranking Method for Microscopy
Koho, S., Fazeli, E., Eriksson, J., & Hanninen, P. E. (2016) · Scientific Reports · doi:10.1038/srep28962 · Cited by 52
Optimal Transmission Estimation via Fog Density Perception for Efficient Single Image Defogging
Ling, Z., Gong, J., Fan, G., & Lu, X. B. (2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2778565 · Cited by 52
“Suesstrunk [36] proposed 12 features, including statistics of normalized luminance [35], statistics of MSCN products [31], [40], gradient statistics, statistics of colors [35] and so on, to measure”
BackgroundNR-GVQM: A No Reference Gaming Video Quality Metric
Zadtootaghaj, S., Barman, N., Schmidt, S., Martini, M. G., & Möller, S. (2018) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism.2018.00031 · Cited by 52
“We observe that using just four features (NIQE, TI, Blockiness and Blur) can give a model with an accuracy of 0.96 which has a low computation but still a high correlation with the actual value of VMAF.”
BackgroundInfluentialKim, G., Kwon, D., & Kwon, J. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803328 · Cited by 52
“For evaluation, the naturalness image quality evaluator (NIQE) [25] was used, which is a no-reference metric that can measure image quality without ground-truth.”
MethodTowards a video quality assessment based framework for enhancement of laparoscopic videos
Khan, Z. A., Beghdadi, A., Cheikh, F. A., Kaaniche, M., Pelanis, E., Palomar, R., Fretland, Å. A., Edwin, B., & Elle, O. J. (2020) · SPIE Medical Imaging: Image Perception, Observer Performance, and Technology Assessment · doi:10.1117/12.2549266 · Cited by 52
Underwater image restoration: A state‐of‐the‐art review
Fayaz, S., Parah, S. A., Qureshi, G. J., & Kumar, V. (2020) · IET Image Processing · doi:10.1049/ipr2.12041 · Cited by 52
“(ii) NIQE: It is calculated using natural scene statistic (NSS) features from patches having dimensions p × p of picture which is to be assessed, fitting these with MVG representation, and afterwards comparing this MVG fit with natural MVG representation.”
BackgroundInfluentialJin, Y., Chen, M., Goodall, T., Patney, A., & Bovik, A. C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3087322 · Cited by 52
“We compared 5 NR algorithms on both the 2D and 3D databases: BRISQUE [39], NIQE [40], SVBRISQUE [68], V-BLIINDS [60], and TLVQM [62].”
MethodSelf-citationRegion-Adaptive Deformable Network for Image Quality Assessment
Shi, S., Bai, Q., Cao, M., Xia, W., Wang, J., Chen, Y., & Yang, Y. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00042 · Cited by 52
Single-Image Super Resolution of Remote Sensing Images with Real-World Degradation Modeling
Zhang, J., Xu, T., Li, J., Jiang, S., & Zhang, Y. (2022) · Remote Sensing · doi:10.3390/rs14122895 · Cited by 52
“Non-referenced metrics such as NIQE and ENIQA are also defined on feature spaces, thus they also focus on the edge parts of the images.”
MethodInfluentialBlind Quality Assessment for in-the-Wild Images via Hierarchical Feature Fusion Strategy
Sun, W., Duan, H., Min, X., Chen, L., & Zhai, G. (2022) · IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB) · doi:10.1109/bmsb55706.2022.9828590 · Cited by 52
“…and PLCC. 4) Compared Algorithms: We compare the proposed models with eight state-of-the-art BIQA models including hand-crafted feature based BIQA models: NIQE [20], BRISUE [2], and BMPRI [5], and deep learning based BIQA models: CNNIQA [6], WaDIQaM-NR [7], SFA [21], DB-CNN [8], and HyperIQA [9].”
Yan, Z., Wen, F., Ying, R., Ma, C., & Liu, P. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.02782 · Cited by 52
“Basically, this definition of perceptual quality is based on the deviation from natural sample statistics, which correlates well with human subjective score and has been widely used in designing no-reference image quality measures.(Mittal et al., 2013; Wang & Simoncelli, 2005)”
MethodToward a No-Reference Quality Metric for Camera-Captured Images
Hu, R., Liu, Y., Gu, K., Min, X., & Zhai, G. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3128023 · Cited by 51
“For quantifying the commonality of natural images, characterization of the NSS regularities was often employed in the BIQA research [18], [19], [24].”
BackgroundMethodInfluentialMulti-frame super-resolution of remote sensing images using attention-based GAN models
Wang, P., & Sertel, E. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110387 · Cited by 51
A systematic approach for enhancement of homogeneous background images using structural information
Vijayalakshmi, D., & Nath, M. K. (2023) · Graphical Models · doi:10.1016/j.gmod.2023.101206 · Cited by 51
Guo, Y., He, W. P., Xia, Y., & Zhang, H. (2023) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2023.10.014 · Cited by 51
A-ESRGAN: Training Real-World Blind Super-Resolution with Attention U-Net Discriminators
Wei, Z., Huang, Y., Chen, Y., Zheng, C., & Gao, J. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-7025-4_2 · Cited by 51
Brightness Perceiving for Recursive Low-Light Image Enhancement
Wang, H., Peng, L., Sun, Y., Wan, Z., Wang, Y., & Cao, Y. H. (2023) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2023.3339092 · Cited by 51
“For no-reference metrics, we use NIQE ↓ [51], EME ↑ [52], and LOE ↓ [39] for evaluation.”
MethodDTCNet: Transformer-CNN Distillation for Super-Resolution of Remote Sensing Image
Lin, C., Mao, X., Qiu, C., & Zou, L. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3409808 · Cited by 51
Hou, M., Chen, Y., Li, J., & Yi, F. (2024) · Science Advances · doi:10.1126/sciadv.ado4847 · Cited by 51
“To evaluate the image quality, we used the no reference natu-ral image quality evaluator (NIQE) index ( 30 ) as the metric.”
MethodCLIP-AGIQA: Boosting the Performance of AI-Generated Image Quality Assessment with CLIP
Tang, Z., Wang, Z., Peng, B., & Dong, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78125-4_4 · Cited by 51
Oulmalme, C., Nakouri, H., & Jaafar, F. (2025) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2025.105903 · Cited by 51
Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation
Yang, Y., Shao, J., Li, X., Shen, Y., Geiger, A., & Liao, Y. (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/cvpr52734.2025.00272 · Cited by 51
“The quantitative results are evaluated using the CLIP-Score [24], NIQE [50], and BRISQUE [49] metrics.”
Xie, H., Wen, B., Chen, Z., Hong, F., & Liu, Z. (2026) · International Journal of Computer Vision · doi:10.1007/s11263-026-02999-6 · Cited by 51
“Perceptual no-referencemetrics, such as NIQE (Mittal et al., 2012) and BRISQUE (Mittal et al., 2013), estimate image quality directly from natural image statistics and are occasionally used as complementary signals.”
Temporally Coherent GANs for Video Super-Resolution (TecoGAN).
Chu, M., Xie, Y. X., Leal-Taixé, L., & Thuerey, N. (2018) · Cited by 51
Zhu, W., Zhai, G., Min, X., Hu, M., Liu, J., Guo, G., & Yang, X. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2902484 · Cited by 51
“[2]; 2) popular NR metrics: DIIVINE [8] and NIQE [9]; 3) competitive RR algorithms containing FEDM [23], FSI [16], RRED [21], REDLOG [22].”
BackgroundMethodInfluentialA Fast Sand-Dust Image Enhancement Algorithm by Blue Channel Compensation and Guided Image Filtering
Cheng, Y., Jia, Z., Lai, H., Yang, J., & Kasabov, N. K. (2020) · IEEE Access · doi:10.1109/access.2020.3034151 · Cited by 51
“[9] proposed a sand-dust image enhancement method combining the spatial domain and the transform domain.”
Active Fine-Tuning from gMAD Examples Improves Blind Image Quality Assessment
Wang, Z., & Ma, K. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3071759 · Cited by 51
A multiscale double-branch residual attention network for anatomical–functional medical image fusion
Li, W., Peng, X., Fu, J., Wang, G., Huang, Y., & Chao, F. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.105005 · Cited by 51
Chen, K., Wang, H., Fang, S., Li, X., Ye, M., & Chao, H. J. (2022) · ACM Multimedia Systems Conference (MMSys) · doi:10.1145/3524273.3528184 · Cited by 50
“For example, Naturalness Image Quality Evaluator (NIQE) [24] is based on spatial-specific natural scene statistic features that are derived from local image patches.”
BackgroundDEANet: Decomposition Enhancement and Adjustment Network for Low-Light Image Enhancement
Jiang, Y., Li, L., Zhu, J., Xue, Y., & Ma, H. (2023) · Tsinghua Science & Technology · doi:10.26599/tst.2022.9010047 · Cited by 50
Dilated Convolutional Transformer for High-Quality Image Deraining
Li, Y., Lu, J., Chen, H., Wu, X., & Chen, X. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00442 · Cited by 50
Adversarial Relighting Against Face Recognition
Zhang, Q., Guo, Q., Gao, R., Juefei-Xu, F., Yu, H., & Feng, W. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3380848 · Cited by 50
“In this paper, we use two limited vision image quality assessment metrics, i.e ., BRISQUE [49] and NIQE [50], to compare the image quality of generated adversarial exam-Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
MethodDeep learning for medical imaging super-resolution: A comprehensive review
Xiao, H., Yang, Z., Liu, T., Liu, S., Huang, X., & Dai, J. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.129667 · Cited by 50
S2-Transformer for Mask-Aware Hyperspectral Image Reconstruction
Wang, J., Li, K., Zhang, Y., Yuan, X., & Tao, Z. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3543842 · Cited by 50
“In Table IV, we metrically compare the Transformer-based methods with the no-reference assessment, naturalness image quality evaluator (NIQE) [83].”
Q-Eval-100K: Evaluating Visual Quality and Alignment Level for Text-to-Vision Content
Zhang, Z., Kou, T., Wang, S., Li, C., Sun, W., Wang, W., Li, X., Wang, Z., Cao, X., Min, X., et al. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00993 · Cited by 50
Zhou, J., Zhang, D., He, Z., Gai, Q., & Jiang, Q. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3634001 · Cited by 50
“For perceptual quality assessment, we employ the Natural Image Quality Evaluator (NIQE) [58], the Underwater Color Image Quality Evaluation (UCIQE) [59], and the Underwater Image Quality Measure (UIQM).”
Lv, Y., Jiang, G., Yu, M., Xu, H., Shao, F., & Liu, S. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351221 · Cited by 50
“Natural Image Quality Evaluator (NIQE) [16], QualityAware Clustering (QAC) [17] and Blind Learning of Image Quality using Synthetic Scores (BLISS) [18] are state-ofthe-art models in this category.”
MethodSparse Representation Based Image Quality Index with Adaptive Sub-Dictionaries
Li, L., Cai, H., Zhang, Y., Lin, W., Kot, A. C., & Sun, X. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2577891 · Cited by 50
“By contrast, general-purpose metrics evaluate the overall quality of an image without knowing the distortion types [17].”
BackgroundLightweight Image Super-Resolution by Multi-Scale Aggregation
Wan, J., Yin, H., Liu, Z., Chong, A., & Liu, Y. (2020) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2020.3028356 · Cited by 50
“5, due to the large scaling In order to make the visual comparison more convincing, no-reference (NR) image quality assessment (IQA) algorithms [20], [21], [22], [23], [24] are considered for subjective assessment of image quality.”
BackgroundMethodNoise reduction for sonar images by statistical analysis and fields of experts
Yuan, F., Xiao, F., Zhang, K., Huang, Y., & Cheng, E. (2020) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2020.102995 · Cited by 50
Yang, L., Xu, M., Deng, X., & Feng, B. (2021) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme51207.2021.9428390 · Cited by 50
“Metrics FR-IQA NR-IQAVSI VIF GSM DIVINE ILNIQE NIQE PLCC 0.816 0.851 0.896 0.222 0.648 0.740 SROCC 0.886 0.741 0.898 0.182 0.488 0.698 MAE 6.190 5.492 4.617 9.845 8.042 6.609 Fig.”
BackgroundMethodInfluentialExploring the Effectiveness of Video Perceptual Representation in Blind Video Quality Assessment
Liao, L., Xu, K., Wu, H., Chen, C., Sun, W., Yan, Q., & Lin, W. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3547849 · Cited by 50
“We have evaluated the proposed TPQI on four popular in-thewild video datasets and the results demonstrate that the proposed TPQI achieves almost the same performance as the well-established spatial quality index, NIQE [33], indicating that the temporal quality index can be the same effective as the spatial quality ind…”
BackgroundMethodInfluentialChang, L., Song, H., Li, M., & Xiang, M. (2023) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2023.01.007 · Cited by 50
Generative Adversarial Network-Based Image Super-Resolution Using Perceptual Content Losses
Cheon, M., Kim, J.-H., Choi, J., & Lee, J. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11021-5_4 · Cited by 50
GLEAN: Generative Latent Bank for Image Super-Resolution and Beyond
Chan, K. C. K., Xu, X., Wang, X., Gu, J., & Loy, C. C. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3186715 · Cited by 49
“Since no groundtruth images are available, we use NIQE [69], FID [70], and ArcFace similarity [66] as the evaluationmetrics.”
MethodInfluentialIllumination Guided Attentive Wavelet Network for Low-Light Image Enhancement
Xu, J., Yuan, M., Yan, D.-M., & Wu, T. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3207330 · Cited by 49
“To evaluate no-reference image enhancement, we employ the natural image quality evaluator (NIQE) [60] and perceptual index (PI) [61] as the quantitative metrics.”
MethodLow-light image enhancement by deep learning network for improved illumination map
Wang, M., Li, J., & Zhang, C. (2023) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2023.103681 · Cited by 49
Subjective and Objective Audio-Visual Quality Assessment for User Generated Content
Cao, Y., Min, X., Sun, W., & Zhai, G. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3290528 · Cited by 49
“For visual feature extractors, the handcrafted VQA models include BRISQUE [27], NIQE [28], HIGRADE [29], V-BLIINDS [31], TLVQM [32], VIDEVAL [33], and RAPIQUE [34].”
MethodUnderwater Color Correction Network With Knowledge Transfer
Lin, P., Wang, Y., Li, Y., Fan, Z., & Fu, X. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3374598 · Cited by 49
“The optimal value of NIQE [78] obtained by the designed model presents that the generated images have more natural appearances.”
BackgroundMethodInfluential3DTA: No-Reference 3D Point Cloud Quality Assessment With Twin Attention
Zhu, L., Cheng, J., Wang, X., Su, H., Yang, H., Yuan, H., & Korhonen, J. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3407698 · Cited by 49
Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance
Fan, J., Weng, J., Wang, K., Yang, Y., Qian, J., Li, J., & Yang, 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/cvpr52733.2024.02467 · Cited by 49
“1, our method out-performs SOTAs performance in terms of FADE [8] and NIQE [41] across all collected datasets.”
InfluentialA novel approach for denoising and enhancement of extremely low-light video
Kim, M., Park, D., Han, D. K., & Ko, H. (2015) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2015.7064113 · Cited by 49
Blind image sharpness assessment based on local contrast map statistics
Gvozden, G., Grgić, S., & Grgić, M. (2017) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2017.11.017 · Cited by 49
“In comparison to eight tested methods, namely SSEQ, NIQE, IL-NIQE, LPC-SI, FISH, FISHbb, S3 and MLV the F-test showed that BISHARP is statistically better or indistinguishable on all six databases.”
MethodInfluentialSingle Image Dehazing Based on Adaptive Histogram Equalization and Linearization of Gamma Correction
Thanh, L. T., Thanh, D. N. H., Hue, N. M., & Prasath, V. B. S. (2019) · Asia-Pacific Conference on Communications (APCC) · doi:10.1109/apcc47188.2019.9026457 · Cited by 49
“The NIQE [19] The smaller value of NIQE, the better perceptual quality.”
BackgroundXu, C., Peng, Z., Hu, X., Zhang, W., Chen, L., & An, F. (2020) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2020.3010634 · Cited by 49
“Entropy [48], Structural Similarity (SSIM) [49], Peak Signal to Noise Ratio (PSNR), and Natural Image Quality Evaluator (NIQE) [50] are the chosen IQA metrics, in which entropy reflects the on hazy images, but has very poor performance on low-light images.”
BackgroundBlind quality assessment of night-time image
Hu, R., Liu, Y., Wang, Z., & Li, X. (2021) · Displays · doi:10.1016/j.displa.2021.102045 · Cited by 49
Shen, W., Zhou, M., Liao, X., Jia, W., Xiang, T., Fang, B., & Shang, Z. (2022) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2022.3164332 · Cited by 49
“We compare our method with seven representative state-of-the-art quality prediction methods: the natural image quality evaluator (NIQE) [54], the blind/referenceless image spatial quality evaluator (BRISQUE) [55], VIIDEO [28], VBLIINDS [12], TLVQM [13], VSFA [38], VIDEVAL [29] and VSFA with mixed dataset training (MDT…”
MethodInfluentialAttention-guided dynamic multi-branch neural network for underwater image enhancement
Yan, X., Qin, W., Wang, Y., Wang, G., & Fu, X. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.110041 · Cited by 49
AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos
Wu, Y., Wang, X., Li, G., & Shan, Y. (2022) · neural information processing systems · doi:10.52202/068431-0817 · Cited by 49
A Novel Image Steganographic Approach for Hiding Text in Color Images using HSI Color ModelPreprint
Muhammad, K., Ahmad, J., Farman, H., & Zubair, M. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1503.00388 · Cited by 49
“MN ∑ ∑ (Sxy − Cxy) N y=1 M x=1 (2) Note that here M and N are image dimensions, x and y are loop variables, S is stego image, C is cover image and Cmax is the maximum pixel intensity among both images [27-33].”
BackgroundA super-resolution strategy for mass spectrometry imaging via transfer learning
Liao, T., Ren, Z., Chai, Z., Yuan, M., Miao, C., Li, J., Chen, Q., Li, Z., Wang, Z., Lin, Y., et al. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00677-7 · Cited by 49
Automatic Cataract Severity Detection and Grading Using Deep Learning
Yadav, S. K., & Yadav, J. K. P. S. (2023) · Journal of Sensors · doi:10.1155/2023/2973836 · Cited by 48
“According to the experimental findings presented in references [42, 43], the NIQE and PIQE values for goodquality images do not exceed 5 and 50, respectively.”
BackgroundInfluentialSubjective and objective quality evaluation of UGC video after encoding and decoding
Zhang, Y., Wang, J., Zhu, Y., & Xie, R. (2024) · Displays · doi:10.1016/j.displa.2024.102719 · Cited by 48
Fu, H., Ling, Z., Sun, G., Ren, J., Zhang, A., Zhang, L., & Jia, X. (2024) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2024.09.034 · Cited by 48
Improving long-tailed pest classification using diffusion model-based data augmentation
Du, M., Wang, F., Wang, Y., Li, K., Hou, W., Liu, L., He, Y., & Wang, Y. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.110244 · Cited by 48
Quality assessment for real out-of-focus blurred images
Liu, Y., Gu, K., Zhai, G., Liu, X., Zhao, D., & Gao, W. (2017) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2017.03.007 · Cited by 48
“The rst type belongs to general-purpose NR IQA methods, which includes BIQI, BRISQUE, DESIQUE, DIIVINE, NFERM,295 NIQE, SISBLIM, BQMS and LPSI.”
BackgroundInfluentialTowards Simulating Foggy and Hazy Images and Evaluating Their Authenticity
Zhang, N., Zhang, L., & Cheng, Z. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-70090-8_42 · Cited by 48
“We get inspiration from no-reference image quality assessment [12,13].”
BackgroundAbnormality Detection in Musculoskeletal Radiographs Using Capsule Network
Saif, A. F. M., Shahnaz, C., Zhu, W., & Ahmad, M. O. (2019) · IEEE Access · doi:10.1109/access.2019.2923008 · Cited by 48
“Table 1 shows the Blind Image Spatial Quality Evaluator (BRISQUE) and Naturalness Image Quality Eval-uator (NIQE) score [15], [16].”
BackgroundOpenHSV: an open platform for laryngeal high-speed videoendoscopy
Kist, A. M., Dürr, S., Schützenberger, A., & Döllinger, M. (2021) · Scientific Reports · doi:10.1038/s41598-021-93149-0 · Cited by 48
Learning the Non-differentiable Optimization for Blind Super-Resolution
Zheng, H., Li, J., Wang, X., & Gao, X. (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/cvpr46437.2021.00213 · Cited by 48
“The fidelity-oriented SR results are evaluated with PSNR and SSIM, and the perception-driven SR images are measured by learned perceptual image patch similarity (LPIPS) [36], and NIQE [24].”
MethodInfluentialSpatiotemporal Representation Learning for Blind Video Quality Assessment
Liu, Y., Wu, J., Li, L., Dong, W., Zhang, J., & Shi, G. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3114509 · Cited by 48
Linear Contrast Enhancement Network for Low-Illumination Image Enhancement
Zhou, Z., Shi, Z., & Ren, W. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3232641 · Cited by 48
“To evaluate the performance of the proposed method, we adopt for metrics: the natural image quality evaluator (NIQE) [50], the lightness order error (LOE) [43], the peak signal-to-noise ratio (PSNR), and the Structural SIMilarity (SSIM) [51].”
MethodCao, Y., Wan, Z., Ren, D., Yan, Z., & Zuo, W. (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/cvpr52688.2022.00576 · Cited by 47
“Category PLCC SRCC Methods Category PLCC SRCC MA [41] NR 0.203 0.201 PSNR FR 0.292 0.255 PI [5] 0.166 0.169 SSIM [58] 0.398 0.340 NIQE [43] 0.102 0.064 LPIPS-Alex [73] 0.646 0.628 VIF [48] FR 0.524 0.433 LPIPS-VGG [73] 0.647 0.591 VSNR [7] 0.375 0.321 PieAPP [46] 0.697 0.706 VSI [70] 0.516 0.450…”
InfluentialMitigating Artifacts in Real-World Video Super-resolution Models
Xie, L., Wang, X., Shi, S., Gu, J., Dong, C., & Shan, Y. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i3.25398 · Cited by 47
No-reference quality assessment for underwater images
Hou, G., Zhang, S., Lu, T., Li, Y., Pan, Z., & Huang, B. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109293 · Cited by 47
Black-box adversarial attacks against image quality assessment models
Ran, Y., Zhang, A., Li, M., Tang, W., & Wang, Y. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125415 · Cited by 48
Noise Self-Regression: A New Learning Paradigm to Enhance Low-Light Images Without Task-Related Data
Zhang, Z., Zhao, S., Jin, X., Xu, M., Yang, Y., Yan, S., & Wang, M. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3487361 · Cited by 47
“We use three widely-used performance metrics to evaluate the quantitative result of each method, i.e., PSNR, SSIM [35]) and NIQE [27].”
A blind deconvolution model for scene text detection and recognition in video
Khare, V., Shivakumara, P., Paramesran, R., & Blumenstein, M. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.01.008 · Cited by 47
“For the purpose of measuring the quality of the deblurred images, we use standard blind measures, namely, BRISQUE [35], NRIQA [36], GPC [37], and SI [38] as discussed in section 3.1.”
BackgroundMethodInfluentialDeep learning-based image super-resolution considering quantitative and perceptual quality
Choi, J. H., Kim, J., Cheon, M., & Lee, J. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.06.103 · Cited by 47
Dendi, S. V. R., Dev, C., Kothari, N., & Channappayya, S. S. (2018) · IEEE Signal Processing Letters · doi:10.1109/lsp.2018.2879518 · Cited by 47
“IL-NIQE [2] is a variant of NIQE, which models the NSS features of image from multiple cues.”
BackgroundBio-inspired optimization algorithms for real underwater image restoration
Sánchez-Ferreira, C., Coelho, L. D. S., Ayala, H. V. H., Farias, M. C. Q., & Llanos, C. H. (2019) · Signal Processing Image Communication · doi:10.1016/j.image.2019.05.015 · Cited by 47
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.