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 301–400 of 1,013
Magic ELF: Image Deraining Meets Association Learning and Transformer
Jiang, K., Wang, Z., Chen, C., Wang, Z., Cui, L., & Lin, C. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3547760 · Cited by 133
“Quantitative resultsof NIQE[37]andSSEQ[34] are listed in Table 3, where smaller NIQE and SSEQ scores indicate better perceptual quality and clearer contents.”
BackgroundMethodNo-reference image quality assessment based on log-derivative statistics of natural scenes
Zhang, Y., & Chandler, D. M. (2013) · Journal of Electronic Imaging · doi:10.1117/1.jei.22.4.043025 · Cited by 128
Contrast Enhancement Based on Intrinsic Image Decomposition
Yue, H., Yang, J., Sun, X., Wu, F., & Hou, C. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2703078 · Cited by 132
Learning Deep Context-Sensitive Decomposition for Low-Light Image Enhancement
Ma, L., Liu, R., Zhang, J., Fan, X., & Luo, Z. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3071245 · Cited by 132
Robust Representation Learning with Feedback for Single Image Deraining
Chen, C., & Li, H. (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/cvpr46437.2021.00765 · Cited by 132
Wang, Y., Yan, X., Guan, D., Wei, M., Chen, Y., Zhang, X.-P. S., & Li, J. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3170328 · Cited by 134
“Additionally, we utilize four well-known no-reference image assessment metrics to further measure the quality of dehazed images from multiple perspectives, including NIQE [61], BRISQUE [62], SSEQ [63], and FADE [64].”
MethodLight-Guided and Cross-Fusion U-Net for Anti-Illumination Image Super-Resolution
Cheng, D., Chen, L., Lv, C., Guo, L., & Kou, Q. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3194169 · Cited by 134
“The test results are evaluated via several objective metrics, such as Peak Signal-to-Noise Ratio (PSNR) [39], Structural Similarity (SSIM) [40], Learned Perceptual Image Patch Similarity Metric (LPIPS) [41], Natural Image Quality Evaluator (NIQE) [42], and Perceptual Index (PI) [43].”
MethodUID2021: An Underwater Image Dataset for Evaluation of No-Reference Quality Assessment Metrics
Hou, G., Li, Y., Yang, H., Li, K., & Pan, Z. (2023) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3578584 · Cited by 133
“Afterward, Mittal et al. [35] further developed a natural image quality evaluator (NIQE) without training with any human opinion scores.”
BackgroundMethodInfluentialLow-Light Enhancement Method Based on a Retinex Model for Structure Preservation
Zhou, M., Wu, X., Wei, X., Xiang, T., Fang, B., & Kwong, S. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3268867 · Cited by 132
“In addition to subjective quality assessments, we use the nat-ural image quality evaluator (NIQE) [48], structural similarity index metric (SSIM) [49] and visual information fidelity (VIF) [50] for objective evaluation.”
MethodCross-Level Interaction and Intralevel Fusion Network for Remote Sensing Image Dehazing
Wen, Y., Gao, T., Chen, T., Li, Z., Liu, M., & Liu, L. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3576979 · Cited by 132
“…the effectiveness of real-world image dehazing, we apply the following perceptual quality metrics, naturalness image quality evaluator (NIQE) [75], neural image assessment (NIMA) [76], multiscale image quality transformer (MUSIQ) [77], and multidimension attention network image quality…”
Joint Residual Learning for Underwater Image Enhancement
Hou, M., Liu, R., Fan, X., & Luo, Z. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451209 · Cited by 131
“The criterion we adopt are three popular metrics: the Blur Metric (BM) [23], Spatial-Spectral Entropy-based Quality (SSEQ) [24] and Natural Image Quality Evaluator (NIQE) [25].”
MethodNaturalness-Aware Deep No-Reference Image Quality Assessment
Yan, B., Bare, B., & Tan, W. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2904879 · Cited by 131
“Like in the LCNI comparison in the Table IV, our method performs worse than DIQA and IL-NIQE.”
MethodInfluentialBlind Predicting Similar Quality Map for Image Quality Assessment
Pan, D., Shi, P., Hou, M., Ying, Z., Fu, S., & Zhang, Y. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00667 · Cited by 107
Fang, Y., Yan, J., Li, L., Wu, J., & Lin, W. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2781307 · Cited by 130
“There have been also many reduced reference (RR) [22], [24], [48], [49], and no reference (NR) image quality estimation methods [13], [14], [17], [42], [43], [46], [47] proposed”
BackgroundMethodInfluentialA Survey of Restoration and Enhancement for Underwater Images
Zhang, W., Dong, L., Pan, X., Zou, P., Qin, L., & Xu, W. (2019) · IEEE Access · doi:10.1109/access.2019.2959560 · Cited by 127
Frequency-Oriented Efficient Transformer for All-in-One Weather-Degraded Image Restoration
Gao, T., Wen, Y., Zhang, K., Zhang, J., Chen, T., Liu, L., & Luo, W. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3299324 · Cited by 128
“We choose two unsupervised metrics, naturalness image quality evaluator (NIQE) [105] and spatial-spectral entropy-based quality (SSEQ) [106], to objectively measure the performance of our AIRFormer and other methods on real-world degraded images.”
MethodBlind Image Quality Assessment With Active Inference
Ma, J., Wu, J., Li, L., Dong, W., Xie, X., Shi, G., & Lin, W. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3064195 · Cited by 126
Low-Light Image Enhancement With Multi-Scale Attention and Frequency-Domain Optimization
He, Z., Ran, W., Liu, S., Li, K., Lu, J., Xie, C., Liu, Y., & Lu, H. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3313348 · Cited by 126
“We evaluate the visual quality of enhanced images by PSNR [56], SSIM [52], and LPIPS [57], while the naturalness of the no-reference images is measured by the NIQE [58].”
MethodStreaming Video QoE Modeling and Prediction: A Long Short-Term Memory Approach
Eswara, N., Ashique, S., Panchbhai, A., Chakraborty, S., Sethuram, H. P., Kuchi, K., Kumar, A., & Channappayya, S. S. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2895223 · Cited by 124
“We investigate three VQA metrics for STSQ: 1) STRRED [21], a reduced-reference metric, 2) MS-SSIM [28], a full-reference metric, and 3) NIQE [49], a no-reference metric.”
MethodInfluentialSurvey of single image super‐resolution reconstruction
Li, K., Yang, S., Dong, R., Wang, X., & Huang, J. (2020) · IET Image Processing · doi:10.1049/iet-ipr.2019.1438 · Cited by 124
“Natural image quality evaluator (NIQE) [40] is an image quality evaluation algorithm.”
BackgroundUnderwater Image Restoration via Contrastive Learning and a Real-World Dataset
Han, J., Shoeiby, M., Malthus, T., Botha, E., Anstee, J. M., Anwar, S., Wei, R., Armin, M. A., Li, H., & Petersson, L. (2022) · Remote Sensing · doi:10.3390/rs14174297 · Cited by 124
Hybrid CNN-Transformer Feature Fusion for Single Image Deraining
Chen, X., Pan, J., Lu, J., Fan, Z., & Li, H. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i1.25111 · Cited by 123
NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results
Liu, X., Wu, Z., Li, A., Vasluianu, F.-A., Zhang, Y., Gu, S., Zhang, L., Zhu, C., Timofte, R., Jin, Z. J., et al. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00655 · Cited by 124
“For the next competition, we will consider including NIQE [59] along with metrics measuring model efficiency, such as inference time, model parameter count, computational complexity (FLOPs), and memory consumption.”
MethodGroup MAD Competition? A New Methodology to Compare Objective Image Quality Models
Ma, K., Wu, Q., Wang, Z., Duanmu, Z., Yong, H., Li, H., & Zhang, L. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.184 · Cited by 93
“The four distortion types are common in existing IQA databases [27, 23] and many IQA models are claimed to be able to properly handle these distortions [19, 20, 25, 17, 40, 18, 38, 37, 26, 42, 36, 7, 35].”
BackgroundMethodResultInfluentialDecomposition Makes Better Rain Removal: An Improved Attention-Guided Deraining Network
Jiang, K., Wang, Z., Yi, P., Chen, C., Han, Z., Lü, T., Huang, B., & Jiang, J. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3044887 · Cited by 121
“Since the ground truth is unavailable, we thus introduce two additional quantitative indicators without reference, such as Naturalness Image Quality Evaluator (NIQE) [67] and Spatial-Spectral Entropy-based Quality (SSEQ) [68], to distinguish from pixel-based evaluation fashion.”
MethodNon-distortion-specific no-reference image quality assessment: A survey
Manap, R. A., & Shao, L. (2015) · Information Sciences · doi:10.1016/j.ins.2014.12.055 · Cited by 120
A Comprehensive Benchmark for Single Image Compression Artifact Reduction
Liu, J., Liu, D., Yang, W., Xia, S., Zhang, X., & Dai, Y. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3007828 · Cited by 121
“In our work, we calculate values for NIQE, BRISQE, and ENIQA with the codes provided by their authors using the default settings.”
MethodInfluentialXiao, Y., Yuan, Q., He, J., Zhang, Q., Sun, J., Su, X. B., Wu, J., & Zhang, L. (2022) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2022.102731 · Cited by 120
“Besides, we introduced a reference-free image quality evaluation index NIQE (Mittal et al., 2012).”
MethodVisualQuality-R1: Reasoning-Induced Image Quality Assessment via Reinforcement Learning to Rank
Wu, T., Zou, J., Liang, J., Zhang, L., & Ma, K. (2025) · neural information processing systems · doi:10.52202/085713-2947 · Cited by 120
Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare
Zhu, H., Wu, H., Li, Y., Zhang, Z., Chen, B., Zhu, L., Fang, Y., Zhai, G., Lin, W., & Wang, S. (2024) · neural information processing systems · doi:10.52202/079017-1024 · Cited by 120
Learning a blind quality evaluation engine of screen content images
Gu, K., Zhai, G., Lin, W., Yang, X., & Zhang, W. (2016) · Neurocomputing · doi:10.1016/j.neucom.2015.11.101 · Cited by 118
“Using the newly released SIQAD database [14, 15], the performance of our BQMS model is computed and compared with state-of-the-art IQA techniques, consisting of: 1) FR FSIM [6], GSI [7], IGM [9], VSI [10] and SIQM [13]; 2) RR FEDM [17], QFTB [18] and SDM [19]; 3) NR DIIVINE [26], BLIINDS-II [27], BRISQUE [28], NIQE [2…”
BackgroundMethodInfluentialRestoring Extremely Dark Images in Real Time
Lamba, M., & Mitra, K. (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/cvpr46437.2021.00349 · Cited by 119
“+ NO Retrain GT PSNR/SSIM are known to correlate less with human visual perception [5] as compared to recent perceptual quality metrics Ma [43] and NIQE [47].”
UIF: An Objective Quality Assessment for Underwater Image Enhancement
Zheng, Y., Chen, W., Lin, R., Zhao, T., & Callet, P. L. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3196815 · Cited by 118
“On the other hand, no-reference IQA approaches have achieved significant performances to evaluate generic images [14, 29, 30, 38, 42].”
BackgroundMethodLow-Light Image Enhancement: A Comparative Review and Prospects
Kim, W. (2022) · IEEE Access · doi:10.1109/access.2022.3197629 · Cited by 118
Sobbahi, R. A., & Tekli, J. (2022) · Signal Processing Image Communication · doi:10.1016/j.image.2022.116848 · Cited by 119
Diffusion Models, Image Super-Resolution, and Everything: A Survey
Moser, B. B., Shanbhag, A. S., Raue, F., Frolov, S., Palacio, S., & Dengel, A. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3476671 · Cited by 117
“This can be opinion-and distortion-aware like BRISQUE [57] or opinion-and distortion-unaware like NIQE [58].”
Kwan, C., Budavari, B., Bovik, A. C., & Marchisio, G. (2017) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2017.2737820 · Cited by 117
“In the remote sensed image field, some algorithms have been developed for assessing the quality of color/gray images [19], [20] and multispectral images [1], [22], where the pan band overlaps with the LR multispectral bands.”
BackgroundMethodSelf-citationHuang, Z., Zhang, Y., Li, Q., Li, X., Zhang, T., Sang, N., & Hong, H. (2020) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.2978276 · Cited by 117
“Q-Metric (QM) [5] to evaluate the denoising performance and the natural image quality evaluator (NIQE) [86] are employed to evaluate the improved results obtained by the above-mentioned advanced methods.”
MethodWang, C., & Song, L. (2023) · Information Sciences · doi:10.1016/j.ins.2023.119166 · Cited by 117
Feature-based prediction of streaming video QoE: Distortions, stalling and memory
Bampis, C. G., & Bovik, A. C. (2018) · Signal Processing Image Communication · doi:10.1016/j.image.2018.05.017 · Cited by 116
Self-citationA no-reference metric for evaluating the quality of motion deblurring
Liu, Y., Wang, J., Cho, S., Finkelstein, A., & Rusinkiewicz, S. M. (2013) · ACM Transactions on Graphics · doi:10.1145/2508363.2508391 · Cited by 116
Benchmarking Underwater Image Enhancement and Restoration, and Beyond
Hou, G., Zhao, X., Pan, Z., Yang, H., Tan, L., & Li, J. (2020) · IEEE Access · doi:10.1109/access.2020.3006359 · Cited by 115
“…employ five NR metrics namely blind reference-less image spatial quality evaluator (BRISQUE) [48], naturalness image quality evaluator (NIQE) index [49], multi-task end-to-end optimized deep neural network (MEON) [53], underwater color image quality evaluation (UCIQE) [54], and underwater image…”
BackgroundMethodA Comprehensive Review of Deep Learning-Based Real-World Image Restoration
Zhai, L., Wang, Y., Cui, S., & Zhou, Y. (2023) · IEEE Access · doi:10.1109/access.2023.3250616 · Cited by 116
“The natural image quality evaluator (NIQE) [78] is a completely blind IQA model without any prior knowledge of distortions.”
BackgroundToward Extreme Image Compression With Latent Feature Guidance and Diffusion Prior
Li, Z., Zhou, Y., Hao, W., Ge, C., & Jiang, J. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3455576 · Cited by 115
“…perceptual quality of results, including the Learned Perceptual Image Patch Similarity ( LPIPS ) [53], Naturalness Image Quality Evaluator ( NIQE ) [54], Deep Image Structure and Texture Similarity ( DISTS ) [55], Fréchet Inception Distance ( FID ) [56], and Kernel Inception Distance ( KID ) [57].”
HVI: A New Color Space for Low-light Image EnhancementPreprint
Yan, Q., Feng, Y., Zhang, C., Pang, G., Shi, K., Wu, P., Dong, W., Sun, J., & Zhang, Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.20272 · Cited by 115
“For the unpaired datasets, we evaluate single recovered images using BRISQUE [44] and NIQE [45] perceptually.”
No-Reference Light Field Image Quality Assessment Based on Spatial-Angular Measurement
Shi, L., Zhou, W., Chen, Z., & Zhang, J. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2955011 · Cited by 114
“PSNR [18] [26] [20] [19] [21] [28] [25] [27] [35] [34] [36] [39] [41] [42] [46] [45] [45] [44] [43] [47] [51] Proposed”
BackgroundRasheed, M. T., Shi, D., & Khan, H. (2022) · Signal Processing · doi:10.1016/j.sigpro.2022.108821 · Cited by 114
You Do Not Need Additional Priors or Regularizers in Retinex-Based Low-Light Image Enhancement
Fu, H., Zheng, W., Meng, X., Wang, X., Wang, C., & Ma, H. (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/cvpr52729.2023.01738 · Cited by 114
Blind Image Quality Assessment via Adaptive Graph Attention
Wang, H., Liu, J., Tan, H., Lou, J., Liu, X., Zhou, W., & Liu, H. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3405789 · Cited by 114
“These models include the simulation of perceived structural information in natural scenes as described in Wang et al. [2], as well as the exploration of natural scene statistics (NSS) as detailed in studies by Mittal et al. [10], Moorthy and Bovik [11], and Gao et al. [12].”
MethodAIGIQA-20K: A Large Database for AI-Generated Image Quality Assessment
Li, C., Kou, T., Gao, Y., Cao, Y., Sun, W., Zhang, Z., Zhou, Y., Zhang, Z., Zhang, W., Wu, H., et al. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00636 · Cited by 114
“Including brisque [27], clipiqa [38], cnniqa [13], dbcnn [47], hypetiqa [36], liqe [49], musiq [14], niqe [28], qalign [42], topiq [2], unique [48], and wadiqam [1].”
HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or PixelsPreprint
HunyuanWorld Team, Wang, Z., Liu, Y., Wu, J., Gu, Z., Wang, H., Zuo, X., Huang, T., Li, W., Zhang, S., et al. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.21809 · Cited by 116
“To evaluate the visual quality, we employ a few non-reference image quality assessment metrics, including BRISQUE [31], NIQE [32], and Q-Align [59].”
No-Reference Hyperspectral Image Quality Assessment via Quality-Sensitive Features Learning
Yang, J., Zhao, Y., Yi, C., & Chan, J. C.-W. (2017) · Remote Sensing · doi:10.3390/rs9040305 · Cited by 113
“Since there is no distortion in the training set, the normal distribution of the features is represented by the learned MVG model, which is a benchmark for assessing distorted image [18].”
BackgroundMethodInfluentialÖksüz, İ., Ruijsink, B., Anton, E. P., Clough, J. R., da Cruz, G. J. L., Bustin, A., Prieto, C., Botnar, R. M., Rueckert, D., Schnabel, J. A., et al. (2019) · Medical Image Analysis · doi:10.1016/j.media.2019.04.009 · Cited by 113
Ghost-free multi exposure image fusion technique using dense SIFT descriptor and guided filter
Hayat, N., & Imran, M. (2019) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2019.06.002 · Cited by 113
GCFSR: a Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors
He, J., Wu, S., Chen, K., Fu, L., & Dong, 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/cvpr52688.2022.00193 · Cited by 113
“For evaluation, we employ the widely used non-reference perceptual metrics: FID [12] and NIQE [24].”
MethodBilevel Fast Scene Adaptation for Low-Light Image Enhancement
Ma, L., Jin, D., An, N., Liu, J., Fan, X., Luo, Z., & Liu, R. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-023-01900-z · Cited by 113
“9, the proposed RBL achieved significant improvements over BL in both DE and NIQE, outperforming other methods and demonstrating that our method could obtain the enhancement results whose texture detail and color were more in line with human visual habits.”
MethodEmpowering Low-Light Image Enhancer through Customized Learnable Priors
Zheng, N., Zhou, M., Dong, Y., Rui, X., Huang, J., Li, C., & Zhao, F. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01154 · Cited by 113
Unsupervised Low-Light Image Enhancement Using Bright Channel Prior
Lee, H., Sohn, K., & Min, D. (2020) · IEEE Signal Processing Letters · doi:10.1109/lsp.2020.2965824 · Cited by 112
“We adopted two no-reference metrics widely used in low-light image enhancement for performance evaluation: naturalness image quality evaluator (NIQE) [39] and lightness order error (LOE) [9], which measure the image naturalness and the lightness distortion, respectively.”
MethodBest-Buddy GANs for Highly Detailed Image Super-resolution
Li, W., Zhou, K., Qi, L., Lu, L., & Lu, J. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20030 · Cited by 112
A Survey on Multimedia Services QoE Assessment and Machine Learning-Based Prediction
Kougioumtzidis, G., Poulkov, V. K., Zaharis, Z. D., & Lazaridis, P. I. (2022) · IEEE Access · doi:10.1109/access.2022.3149592 · Cited by 115
“Natural image quality evaluator (NIQE) relies on the development of a quality-aware set of statistical characteristics that stem from a space domain natural scene statistic (NSS) framework [70].”
BackgroundUnsupervised Deraining: Where Contrastive Learning Meets Self-similarity
Ye, Y., Yu, C., Chang, Y., Zhu, L., Zhao, X.-L., Yan, L., & Tian, Y. (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/cvpr52688.2022.00573 · Cited by 114
“We employ the full-reference PSNR and SSIM to evaluate the deraining performance, and also the no-reference natural image quality evaluator (NIQE) [38] for comprehensive evaluation.”
MethodLow-light image enhancement using gamma correction prior in mixed color spaces
Jeon, J. J., Park, J. Y., & Eom, I. K. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2023.110001 · Cited by 113
No-reference image quality assessment algorithms: A survey
Kamble, V. M., & Bhurchandi, K. M. (2015) · Optik · doi:10.1016/j.ijleo.2015.02.093 · Cited by 112
Progressive Dual-Domain Filter for Enhancing and Denoising Optical Remote-Sensing Images
Huang, Z., Zhang, Y., Li, Q., Zhang, T., Sang, N., & Hong, H. (2018) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2018.2796604 · Cited by 111
“The HE method yields the lowest DE and Q-Metric values and the highest NIQE values for each lowquality remote-sensing image, whereas our method produces the highest DE and Q-Metric values and the lowest NIQE values.”
MethodDisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessment
Wu, H., Chen, C., Liao, L., Hou, J., Sun, W., Yan, Q., & Lin, W. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3249741 · Cited by 111
“For example, NIQE [20] and BRISQUE [21] introduce the natural scene statistics (NSS) for general quality predictions,”
BackgroundDuarte-Salazar, C. A., Castro-Ospina, A. E., Becerra, M. A., & Delgado‐Trejos, E. (2020) · IEEE Access · doi:10.1109/access.2020.2967178 · Cited by 111
“This idea was further expanded by popularmethods such asDIIVINE [109], BRISQUE [110], BLIIND-II [114], and NIQE [115], which quantify perceptual quality employing several deviation measurements based on statistics of natural images in the spatial, wavelet, and cosine (DCT) domain [98].”
MethodA Systematic Survey of Deep Learning-Based Single-Image Super-Resolution
Li, J., Pei, Z., Li, W., Gao, G., Wang, L., Wang, Y., & Zeng, T. (2024) · ACM Computing Surveys · doi:10.1145/3659100 · Cited by 111
“Chen et al. [26] proposed a novel Dual Aggregation Transformer (DAT) for SISR, which aggregates features across spatial and channel dimensions, in the interblock and intra-block dual manner.”
BackgroundToward Bridging the Simulated-to-Real Gap: Benchmarking Super-Resolution on Real Data
Köhler, T., Bätz, M., Naderi, F., Kaup, A., Maier, A., & Rieß, C. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2917037 · Cited by 110
“We additionally use five popular no-reference measures, namely S3 [67], BRISQUE [68], SSEQ [69], NIQE [70], and SRM [71], which is a recent measure trained from SISR examples.”
MethodYou Only Need One Color Space: An Efficient Network for Low-light Image EnhancementPreprint
Yan, Q., Feng, Y., Zhang, C., Wang, P., Wu, P., Dong, W., Sun, J., & Zhang, Y. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.05809 · Cited by 110
“For the unpaired datasets, we evaluated single recovered images using BRISQUE [47] and NIQE [48] perceptually.”
MethodMultimodal MRI synthesis using unified generative adversarial networks
Dai, X., Lei, Y., Fu, Y., Curran, W. J., Liu, T., Mao, H. Z., & Yang, X. (2020) · Medical Physics · doi:10.1002/mp.14539 · Cited by 110
“To quantitatively assess the performance of our proposed method for multimodal MR image synthesis, quantities including normalized mean absolute error (NMAE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM) 46 , visual information fidelity (VIF) 47 , and naturalness image quality evaluator (NIQE)…”
MethodInfluentialLow-Light Image Enhancement by Retinex-Based Algorithm Unrolling and Adjustment
Liu, X., Xie, Q., Zhao, Q., Wang, H., & Meng, D. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3289626 · Cited by 108
“3) Evaluation Metrics: We adopt totally five metrics, including peak signal-to-noise ratio (PSNR), SSIM [64], natu-ral image quality evaluator (NIQE) [73], lightness order error (LOE) [7], and LOE ref [18], to comprehensively assess the performance of all competing methods.”
MethodBlind Image Quality Assessment Using Semi-supervised Rectifier Networks
Tang, H., Joshi, N., & Kapoor, A. (2014) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2014.368 · Cited by 108
“al [7] train a Gaussian model of carefully designed features.”
BackgroundRIRNet: Recurrent-In-Recurrent Network for Video Quality Assessment
Chen, P., Li, L., Ma, L., Wu, J., & Shi, G. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413717 · Cited by 108
Real-world Video Super-resolution: A Benchmark Dataset and A Decomposition based Learning Scheme
Yang, X., Xiang, W., Zeng, H., & Zhang, L. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00474 · Cited by 108
Multi-Scale Fusion and Decomposition Network for Single Image Deraining
Wang, Q., Jiang, K., Wang, Z., Ren, W., Zhang, J., & Lin, C. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3334556 · Cited by 108
“For datasets without ground truth, we adopt Naturalness Image Quality Evaluator (NIQE) [55] and Spatial-Spectral Entropy-based Quality (SSEQ) [56] for quantitative comparisons.”
MethodBlind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel
Yue, Z., Zhao, Q., Xie, J., Zhang, L., Meng, D., & Wong, K.-Y. K. (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/cvpr52688.2022.00217 · Cited by 107
“As pointed out by [60], we also find that current non-reference metrics (e.g., NIQE [34], NRQM [28], and PI [1]) are not consistent with our perceptual visual system in real SISR task.”
MethodResultEnhancing images of shale formations by a hybrid stochastic and deep learning algorithm
Kamrava, S., Tahmasebi, P., & Sahimi, M. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.07.009 · Cited by 106
Similarity and quality metrics for MR image-to-image translation
Dohmen, M., Klemens, M., Baltruschat, I. M., Truong, T., & Lenga, M. (2025) · Scientific Reports · doi:10.1038/s41598-025-87358-0 · Cited by 108
“Due to the characteristics of the training set and assumed differences to MR images regarding intensity value distributions, the NIQE metric may not be directly transferable to MR images.”
Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized StylizationPreprint
Yang, T., Wu, R., Ren, P., Xie, X., & Zhang, L. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.14469 · Cited by 106
“It can be seen that our PASD method can generate more realistic details with better visual quality (see the synthesized textures in fur, flowers, leaves, feathers, etc.).”
MethodSeD: Semantic-Aware Discriminator for Image Super-Resolution
Li, B., Li, X., Zhu, H., Jin, Y., Feng, R., Zhang, Z., & Chen, 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/cvpr52733.2024.02436 · Cited by 105
“Furthermore, we adopt the well-known no-reference metric NIQE [11] for the quantitative comparison, since the ground-truth images are not available in the real world.”
Blind Natural Video Quality Prediction via Statistical Temporal Features and Deep Spatial Features
Korhonen, J., Su, Y., & You, J. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413845 · Cited by 103
“Image quality models of this category, for example NIQE [23], BRISQUE [24], HIGRADE [25], and FRIQUEE [26], typically use features based on the principles of natural scene statistics.”
MethodFu, J., Li, W., Du, J., & Xu, L. (2021) · Information Sciences · doi:10.1016/j.ins.2021.06.083 · Cited by 104
A deep journey into image enhancement: A survey of current and emerging trends
Lepcha, D. C., Goyal, B., Dogra, A., Sharma, K. P., & Gupta, D. N. (2022) · Information Fusion · doi:10.1016/j.inffus.2022.12.012 · Cited by 105
Riesz Fractional Based Model for Enhancing License Plate Detection and Recognition
Raghunandan, K. S., Shivakumara, P., Jalab, H. A., Ibrahim, R. W., Kumar, G. H., Pal, U., & Lü, T. (2017) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2017.2713806 · Cited by 103
“More details about NIQE metric can be found in [47].”
BackgroundFast and Efficient Image Quality Enhancement via Desubpixel Convolutional Neural Networks
Vu, T., Nguyen, C. V., Pham, T. X., Luu, T. M., & Yoo, C. D. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11021-5_16 · Cited by 102
No-Reference Video Quality Assessment Using Natural Spatiotemporal Scene Statistics
Dendi, S. V. R., & Channappayya, S. S. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2984879 · Cited by 102
“A case in point is the NIQE index [8].”
BackgroundMethodInfluentialAnalysis of Appeal for Realistic AI-Generated Photos
Göring, S., Rao, R. R. R., Merten, R., & Raake, A. (2023) · IEEE Access · doi:10.1109/access.2023.3267968 · Cited by 103
“In Figure 4, boxplots for the estimated image quality and appeal values of NIMA and NIQE [24] are shown.”
MethodGMS-3DQA: Projection-Based Grid Mini-patch Sampling for 3D Model Quality Assessment
Zhang, Z., Sun, W., Wu, H., Zhou, Y., Li, C., Chen, Z., Min, X., Zhai, G., & Lin, W. (2024) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3643817 · Cited by 102
“The compared NR methods include 3D-NSS [59], BRISQUE [31], and NIQE [32].”
MethodDeep Rectangling for Image Stitching: A Learning Baseline
Nie, L., Lin, C.-Y., Liao, K., Liu, S., & Zhao, Y. (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/cvpr52688.2022.00565 · Cited by 101
A Comprehensive Study of Multimodal Large Language Models for Image Quality Assessment
Wu, T., Ma, K., Liang, J., Yang, Y., & Zhang, L. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72904-1_9 · Cited by 101
NIQSV+: A No-Reference Synthesized View Quality Assessment Metric
Tian, S., Zhang, L., Morin, L., & Déforges, O. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2781420 · Cited by 101
“in [32].”
Su, C.-C., Cormack, L. K., & Bovik, A. C. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2409558 · Cited by 100
“This spatial-domain NSS model has been extended in various ways and successfully deployed in no-reference 2D quality assessment algorithms [9], [10] which deliver highly competitive performance relative to top-performing full-reference metrics.”
BackgroundMethodSelf-citationConditional Variational Image Deraining
Du, Y., Xu, J., Zhen, X., Cheng, M., & Shao, L. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2990606 · Cited by 99
“2) Evaluation Metrics: We adopt three commonly-used metrics, i.e., peak signal to noise ratio (PSNR), structure similarity index (SSIM) [40], and a perception-based metric NIQE [29], to evaluate the performance of deraining on synthesized datasets.”
BackgroundInfluentialUnderwater Image Enhancement With Reinforcement Learning
Sun, S., Wang, H., Zhang, H., Li, M., Xiang, M., Luo, C. L., & Ren, P. (2022) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2022.3152519 · Cited by 99
“These metrics include NIQE [51], UCIQE [52], Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
MethodA Comprehensive Review on Analysis and Implementation of Recent Image Dehazing Methods
Agrawal, S. C., & Jalal, A. S. (2022) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-022-09755-2 · Cited by 99
“GT images are not available for these images; therefore, evaluation is done by a variety of non-reference metrics including FADE, Blur, BALC, , e, r, NIQE, BRISQUE, BLIINDSII and BIQI.”
MethodInfluentialConfusing Image Quality Assessment: Toward Better Augmented Reality Experience
Duan, H., Min, X., Zhu, Y., Zhai, G., Yang, X., & Callet, P. L. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3220404 · Cited by 99
“quality evaluator (NIQE) [30], blind quality assessment based”
BackgroundEarly Stopping for Deep Image PriorPreprint
Wang, H., Li, T., Zhuang, Z., Chen, T., Liang, H., & Sun, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.06074 · Cited by 99
“Comparison with baseline methods It is natural to expect that no-reference image quality assessment (NR-IQA), such as the classic BRISQUE [29], NIQE [30] or state-ofthe-art (SOTA) DNN-based NIMA [38] can possibly make good ES criteria.”
BackgroundSubjective and Objective Quality Assessment of Stitched Images for Virtual Reality
Madhusudana, P. C., & Soundararajan, R. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2921858 · Cited by 98
“Before computing LCC, the scores predicted from the objective algorithm were passed through a five parameter logistic non-linearity described in [47] as We compare the performance of SIQE against existing NR IQA indices such as DIIVINE [10], BRISQUE [11] and NIQE [12] in Table V.”
MethodSelf-citationHuang, Z., Wang, Z., Zhang, J., Li, Q., & Shi, Y. (2020) · Optik · doi:10.1016/j.ijleo.2020.165877 · Cited by 98
Two-Branch Deep Neural Network for Underwater Image Enhancement in HSV Color Space
Hu, J., Jiang, Q., Cong, R., Gao, W., & Shao, F. (2021) · IEEE Signal Processing Letters · doi:10.1109/lsp.2021.3099746 · Cited by 98
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.