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 701–800 of 1,013
Microsaccade-inspired event camera for robotics
He, B., Wang, Z., Zhou, Y., Chen, J., Singh, C. D., Li, H., Gao, Y., Shen, S., Wang, K., Cao, Y., et al. (2024) · Science Robotics · doi:10.1126/scirobotics.adj8124 · Cited by 62
“For this experiment, we first extracted the edges in the grayscale images using the Canny edge detector ( 40 ).”
MethodQu, B., Liang, X., Sun, S., & Gao, W. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00659 · Cited by 61
“Classic NR-VQA meth-ods adopt handcrafted features as evaluation metrics [3, 15, 16, 29, 35, 40].”
LMM-PCQA: Assisting Point Cloud Quality Assessment with LMM
Zhang, Z., Wu, H., Zhou, Y., Li, C., Sun, W., Chen, C., Min, X., Liu, X., Lin, W., & Zhai, G. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680946 · Cited by 61
Advancing Zero-Shot Digital Human Quality Assessment Through Text-Prompted Evaluation
Zhang, Z., Sun, W., Zhou, Y., Wu, H., Li, C., Min, X., Liu, X., Zhai, G., & Lin, W. (2025) · IEEE Transactions on Image Processing · doi:10.1109/tip.2025.3570597 · Cited by 62
“2) Zero-Shot NR Methods: These methods comprise CPBD [42], pretrained BRISQUE* [41], NIQE [10], and IL-NIQE [49].”
Video Compression Dataset and Benchmark of Learning-Based Video-Quality Metrics
Antsiferova, A., Lavrushkin, S., Smirnov, M., Gushchin, A., Vatolin, D. S., & Kulikov, D. (2022) · neural information processing systems · doi:10.52202/068431-1004 · Cited by 61
Can Signal-to-Noise Ratio Perform as a Baseline Indicator for Medical Image Quality Assessment
Zhang, Z., Dai, G., Liang, X., Yu, S., Li, L., & Xie, Y. (2018) · IEEE Access · doi:10.1109/access.2018.2796632 · Cited by 64
“It is observed that, when SNRwm performs the reference score, BRISQUE demonstrates the notable performance that show good prediction on T∗2, T1 and T1C weighted images, followed by BLIINDS-II VOLUME 6, 2018 11537 (T∗2 and T2), NIQE (T1 and T1C) and BIQI (T ∗ 2); while when using SNRcsf as the reference score, only BLI…”
MethodInfluentialDeep neural network for blind visual quality assessment of 4K content
Lu, W., Sun, W., Min, X., Zhu, W., Zhou, Q., He, J., Wang, Q., Zhang, Z., Wang, T., & Zhai, G. (2023) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2022.3221689 · Cited by 60
“Common NSS based methods include blind image spatial quality evaluator (BRISQUE) [23], natural image quality evaluator (NIQE) [26], integrated local NIQE (ILNIQE) [65] and so on.”
InfluentialHuman Motion Video Generation: A Survey
Xue, H., Luo, X., Hu, Z., Zhang, X., Xiang, X., Dai, Y., Liu, J., Zhang, Z., Li, M., Yang, J. J., et al. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3594034 · Cited by 60
VQA 2 : Visual Question Answering for Video Quality Assessment
Jia, Z., Zhang, Z., Qian, J., Wu, H., Sun, W., Li, C., Liu, X., Lin, W., Zhai, G., & Min, X. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3754696 · Cited by 60
BSD: Blind image quality assessment based on structural degradation
Li, Q., Lin, W., & Fang, Y. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.09.105 · Cited by 60
Predicting the Quality of Compressed Videos With Pre-Existing Distortions
Yu, X., Birkbeck, N., Wang, Y., Bampis, C. G., Adsumilli, B., & Bovik, A. C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3107213 · Cited by 60
“For comparison, we tested against prominent FR and RR models: PSNR, MS-SSIM, FSIM, ST-MAD, VSI, and our previously developed 2stepQA, and NR models: NIQE, BRISQUE, V-BLIINDS, and TLVQM.”
MethodInfluentialSelf-citationRegion-Based Dehazing via Dual-Supervised Triple-Convolutional Network
Shin, J., Park, H., & Paik, J. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3050053 · Cited by 60
Automatic underwater polarization imaging without background region or any prior
Wang, H., Hu, H., Jiang, J., Li, X., Zhang, W., Cheng, Z., & Liu, T. (2021) · Optics Express · doi:10.1364/oe.434398 · Cited by 60
Luo, X., Zhang, X., Yoo, P., Martin-Brualla, R., Lawrence, J., & Seitz, S. M. (2021) · ACM Transactions on Graphics · doi:10.1145/3478513.3480485 · Cited by 59
“Our results is shown to produce more details and outperform all baseline methods in NIQE.”
MethodInfluentialChipQA: No-Reference Video Quality Prediction via Space-Time Chips
Ebenezer, J. P., Shang, Z., Wu, Y., Wei, H., Sethuraman, S., & Bovik, A. C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3112055 · Cited by 59
“We also studied performance when just the ST Chips, ST Gradient Chips, and the NIQE features were used.”
BackgroundInfluentialSelf-citationFu, J., Zhou, W., Jiang, Q., Liu, H., & Zhai, G. (2024) · IEEE Signal Processing Letters · doi:10.1109/lsp.2024.3420083 · Cited by 59
“In the early stage, blind IQA metrics are designed based on handcrafted features, e.g., mean subtracted contrast normalized coefficients [2], [3], [4], visual neuron matrix [5], and edge gradient features [6].”
MethodInfluentialLatent Watermark: Inject and Detect Watermarks in Latent Diffusion Space
Meng, Z., Peng, B., & Dong, J. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3535300 · Cited by 59
“Considering all the metrics, we recommend selecting Channel 0 for injecting watermarks.”
InfluentialLMM-VQA: Advancing Video Quality Assessment With Large Multimodal Models
Ge, Q., Sun, W., Zhang, Y., Li, Y., Ji, Z., Sun, F., Jui, S., Min, X., & Zhai, G. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3571788 · Cited by 59
“For instance, NIQE [41] and BRISQUE [39] first introduce natural scene statistics (NSS) for general quality predictions.”
BackgroundHaider, Z. A., Amin, S. U., Fayaz, M., Khan, F. M., Moon, H., & Seo, S. (2025) · Pattern Recognition · doi:10.1016/j.patcog.2025.112890 · Cited by 59
No reference image quality classification for JPEG-distorted images
Corchs, S., Gasparini, F., & Schettini, R. (2014) · Digit. Signal Process. · doi:10.1016/j.dsp.2014.04.003 · Cited by 56
“The subjective scores are obtained from the psycho-visual experiments conducted to assess IQ.”
MethodTian, S., Zhang, L., Morin, L., & Olivier Déforges, A. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2875307 · Cited by 59
“in [63].”
A Hybrid L2 −LP Variational Model For Single Low-Light Image Enhancement With Bright Channel Prior
Fu, G., Duan, L., & Xiao, C. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803197 · Cited by 59
“Since the ground truth of the enhanced image is almost impossible to get, we adopt natural image quality evaluator (NIQE) [22] and autoregressiveTable 1.”
MethodInfluentialSegmented Spherical Projection-Based Blind Omnidirectional Image Quality Assessment
Zheng, X., Jiang, G., Yu, M., & Jiang, H. (2020) · IEEE Access · doi:10.1109/access.2020.2972158 · Cited by 59
“The BIQA methods selected include BRISQUE [15], OG [16], NIQE [17], dip_IQ [18] and BPRI [19].”
MethodImage Quality Assessment for Perceptual Image Restoration: A New Dataset, Benchmark and MetricPreprint
Gu, J., Cai, H., Chen, H., Ye, X., Ren, J., & Dong, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.15002 · Cited by 59
DiffuseTrace: A Transparent and Flexible Watermarking Scheme for Latent Diffusion ModelPreprint
Lei, L., Gai, K., Yu, J., & Zhu, L. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.02696 · Cited by 60
“We evaluate the quality of an image through two no-reference metrics, the Natural Image Quality Evaluator (NIQE) score [49] and the Perceptual Image Quality Evaluator (PIQE) score [50].”
Image Quality Assessment: From Mean Opinion Score to Opinion Score Distribution
Gao, Y., Min, X., Zhu, Y., Li, J., Zhang, X.-P., & Zhai, G. (2022) · Proceedings of the 30th ACM International Conference on Multimedia · doi:10.1145/3503161.3547872 · Cited by 58
“In the field of IQA, predicting the MOS of image quality is very popular [1, 18, 27, 29, 32, 44, 49].”
BackgroundMethodInfluentialLow-Light Image Enhancement via Stage-Transformer-Guided Network
Jiang, N., Lin, J., Zhang, T., Zheng, H., & Zhao, T. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3239511 · Cited by 58
“…Measure (FSIM) [49] and four no-reference metrics, including Perception-based Image Quality Evaluator (PIQE) [50], Natural Image Quality Evaluator (NIQE) [51], Blind/Referenceless Image Spatial QUality Evaluator (BRISQUE) [52] and No-reference Low-light Image Enhancement Evaluation (NLIEE) [53].”
BackgroundU-shape Transformer for Underwater Image Enhancement
Peng, L., Zhu, C., & Bian, L. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-25063-7_18 · Cited by 58
Multi-Scale Attention Generative Adversarial Network for Medical Image Enhancement
Zhong, G., Ding, W., Chen, L., Wang, Y., & Yu, Y. (2023) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2023.3243920 · Cited by 58
“…four common no-reference quality evaluation indexes: image entropy, average gradient (AVG), blind reference image spatial quality evaluator (Brisque) [37], natural image quality evaluator (NIQE) [38], perception-based image quality evaluator (PIQE) [39] to evaluate the quality of medical images.”
BackgroundLow-light Image Enhancement via a Frequency-based Model with Structure and Texture Decomposition
Zhou, M., Leng, H., Fang, B., Xiang, T., Wei, X., & Jia, W. (2023) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3590965 · Cited by 58
“Objective Quality Assessments: We employ the lightness order error (LOE) [45], noreference image quality assessment metric natural image quality evaluator (NIQE) [33], and perception-based image quality evaluator (PIQE) [35] as our objective metrics to measure the objective performance.”
MethodFast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolution
Laroche, C., Almansa, A., & Coupeté, E. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00519 · Cited by 58
“We compute both classical metrics with full or reduced reference such as PSNR, SSIM [40], LPIPS [50] and FID [14], no-reference metrics to measure perceptual quality such as NIQE [28] and BRISQUE [27] and kernel metrics such as the Mean-Squared Error (MSE)”
MethodRealViformer: Investigating Attention for Real-World Video Super-Resolution
Zhang, Y., & Yao, A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73397-0_24 · Cited by 58
Huang, Y., Miyazaki, T., Liu, X., & Omachi, S. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3584385 · Cited by 60
“These methods included deep bilinear convolutional neural network (DBCNN) [37], naturalness image quality evaluator (NIQE) [38], Contrastive Language-Image pretraining for IQA (CLIP-IQA) [39], and blind/referenceless image spatial quality evaluator (BRISQUE) [40].”
Duanmu, Z., Ma, K., & Wang, Z. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2855403 · Cited by 58
Jakhetiya, V., Gu, K., Singhal, T., Guntuku, S. C., Xia, Z.-F., & Lin, W. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2018.2888861 · Cited by 47
“[10] proposed a completely blind assessment approach known as natural image quality evaluator (NIQE), which did not involve any learning.”
MC360IQA: The Multi-Channel CNN for Blind 360-Degree Image Quality Assessment
Sun, W., Luo, W., Min, X., Zhai, G., Yang, X., Gu, K., & Ma, S. (2019) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas.2019.8702664 · Cited by 58
Anti-spoofing in face recognition-based biometric authentication using Image Quality Assessment
Fourati, E., Elloumi, W., & Chetouani, A. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-019-08115-w · Cited by 58
“More recently, Söllinger et al. [12] have presented a similar study to the one of [16] to counter biometric sensor spoofing for 4 biometric modalities (iris, fingerprint, face and finger vein) based on non-reference IQMs as well as their associated natural scene statistics (NSS).”
MethodHarnessing Multi-View Perspective of Light Fields for Low-Light Imaging
Lamba, M., Rachavarapu, K. K., & Mitra, K. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3045617 · Cited by 59
“We also quantified the quality of the restored test images using recent non-reference perceptual metrics such as NIQE [51] and BRISQUE [52].”
MethodInfluentialNDNetGaming - development of a no-reference deep CNN for gaming video quality prediction
Utke, M., Zadtootaghaj, S., Schmidt, S., Bosse, S., & Möller, S. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09144-6 · Cited by 58
Perceptual Quality Assessment of Internet Videos
Xu, J., Li, J., Zhou, X., Zhou, W., Wang, B., & Chen, Z. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475486 · Cited by 58
“The compared "completely blind" opinion unaware metrics which do not require training include NIQE [32], ILNIQE [53] for IQA and VIIDEO [31] for VQA.”
BackgroundMultisensor Remote Sensing Imagery Super-Resolution with Conditional GAN
Wang, J., Gao, K., Zhang, Z., Ni, C., Hu, Z., Chen, D., & Wu, Q. (2021) · Journal of Remote Sensing · doi:10.34133/2021/9829706 · Cited by 58
“…the di ff erence between ground-truth HR images and super-resolved images, we also adopt two perceptual metrics, i.e., the learned perceptual image patch similarity (LPIPS) [55] metric and naturalness image quality evaluator (NIQE) [59] which can better account for many nuances of human perception.”
MethodMultitemporal and Multispectral Data Fusion for Super-Resolution of Sentinel-2 Images
Tarasiewicz, T., Nalepa, J., Farrugia, R. A., Valentino, G., Chen, M., Briffa, J. A., & Kawulok, M. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3311622 · Cited by 57
“…which are not coupled with any HR reference, we compute SAM after downsampling the super-resolved image back to the LR size to verify the radiometric consistency, and the quality of the super-resolved image is assessed using the reference-less naturalness image quality evaluator (NIQE) [90].”
MethodResultImage deblurring method based on self-attention and residual wavelet transform
Zhang, B., Sun, J., Sun, F., Wang, F., & Zhu, B. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.123005 · Cited by 58
Tu, Z., Yang, X., He, X. G., Yan, J., & Xu, T. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3359095 · Cited by 57
“PI can be obtained by incorporating the criteria of Ma score [87] and natural image quality evaluator (NIQE) [88] as where v 1 and v 2 denote the mean vectors of multivariate Gaussian (MVG) of I HR and MVG of I SR , whereas (cid:54) 1 and (cid:54) 2 denote corresponding covariance matrices of…”
MethodVQCNIR: Clearer Night Image Restoration with Vector-Quantized Codebook
Zou, W., Gao, H., Tian, Y., Chen, L., Yang, W., Huang, S., Chen, H., & Chen, S. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i7.28623 · Cited by 57
Low-dose computed tomography perceptual image quality assessment
Lee, W., Wagner, F., Galdrán, A., Shi, Y., Xia, W., Wang, G., Mou, X., Ahamed, M. A., Imran, A.-A.-Z., Oh, J. E., et al. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103343 · Cited by 57
Blind Image Quality Assessment Based on Geometric Order Learning
Shin, N.-H., Lee, S., & Kim, C. (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/cvpr52733.2024.01216 · Cited by 57
Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Model
Zhang, L., You, W., Shi, K., & Gu, S. (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/cvpr52734.2025.01675 · Cited by 57
“To quantitatively validate the efficacy of the proposed method, we utilize three full-reference metrics: PSNR, SSIM and LPIPS [48]; and four non-reference metrics CLIPIQA [34], MUSIQ [14], MANIQA [42], and NIQE [22] to evaluate the performance.”
A novel deep neural network for noise removal from underwater image
Jiang, Q., Chen, Y., Wang, G., & Ji, T. (2020) · Signal Processing Image Communication · doi:10.1016/j.image.2020.115921 · Cited by 56
Zero-Shot Image Super-Resolution with Depth Guided Internal Degradation Learning
Cheng, X., Fu, Z., & Yang, J. J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58520-4_16 · Cited by 57
Joint Luminance and Chrominance Learning for Underwater Image Enhancement
Xue, X., Hao, Z., Ma, L., Wang, Y., & Liu, R. (2021) · IEEE Signal Processing Letters · doi:10.1109/lsp.2021.3072563 · Cited by 57
“Quantitative Evaluation: Table I reports the quantitative results of different methods in terms of UCIQE [21], UIQM [22] and NIQE [23] on the test set and the proposed method achieves the best evaluation result on almost all the metrics.”
MethodA Hybrid Transformer-Mamba Network for Single Image DerainingPreprint
Sun, S., Ren, W., Zhou, J., Gan, J., Wang, R., & Cao, X. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.00410 · Cited by 57
“As the ground truths of real-world rainy images in Internet-Data [8] are missing, we conduct the qualitative comparison by computing non-reference image quality assessment metrics including NIQE [100] and BRISQUE [101] on 20 randomly sampled images.”
MethodFireRed-Image-Edit-1.0 Technical ReportPreprint
Super Intelligence Team, Qiao, C., Hui, C., Li, C., Wang, C., Song, D., Zhang, J., Li, J., Xiang, Q., Wang, R., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.13344 · Cited by 58
“IQA metrics [24, 23] detect issues like blur, noise, and exposure imbalance, while aesthetics predictors [28] evaluate composition and appeal.”
Huang, Z., & Liu, S. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3027001 · Cited by 56
Computational Optics for Mobile Terminals in Mass Production
Chen, S., Lin, T., Feng, H., Xu, Z., Li, Q., & Chen, Y. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3200725 · Cited by 56
“And the non-reference IQAs, e.g., BRISQUE [59], NIQE [63] are assessing real photograph because obtaining non-degraded reference of real photo is impossible.”
Cross-sensor remote sensing imagery super-resolution via an edge-guided attention-based network
Qiu, Z., Shen, H., Yue, L., & Zheng, G. (2023) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2023.04.016 · Cited by 56
Visual-Instructed Degradation Diffusion for All-in-One Image Restoration
Luo, W., Qin, H., Chen, Z., Wang, L., Zheng, D., Li, Y., Liu, Y., Li, B., & Hu, W. (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/cvpr52734.2025.01191 · Cited by 58
“We draw inspiration from image quality assessment [77, 78, 114] and select TE42 [26], a family of charts commonly used for camera testing and visual analysis, to construct a pool of visual grounds.”
Infrared Image Super-Resolution: A Systematic Review and Future Trends
Huang, Y., Miyazaki, T., Liu, X., & Omachi, S. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3614673 · Cited by 56
“The NIQE [207] is a statisticalcollectionof“quality-aware”featuresbuiltonasimple butsuccessfulNSSmodelinthespatialdomain.”
4KAgent: Agentic Any Image to 4K Super-Resolution
Zuo, Y., Zheng, Q., Wu, M., Jiang, X., Li, R., Wang, J., Zhang, Y., Mai, G., Wang, L. V., Zou, J., et al. (2025) · neural information processing systems · doi:10.52202/085713-5476 · Cited by 56
Face Verification via Learned Representation on Feature-Rich Video Frames
Goswami, G., Vatsa, M., & Singh, R. (2017) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2017.2668221 · Cited by 51
“We also compare the performance of the proposed frame selection approach with frame selection based on no-reference image quality metrics namely BRISQUE [32], NIQE [30], and SSEQ [31].”
BackgroundResultYu, S., Dai, G., Wang, Z., Li, L., Wei, X., & Xie, Y. (2018) · BMC Medical Imaging · doi:10.1186/s12880-018-0256-6 · Cited by 56
“Specifically, to SNRwm, BIQI, BLIINDS-II and BRISQUE on T2 * (rp ≥ 0.78), BRISQUE and NIQE on T1 (rp ≥ 0.77), BLIINDS-II on T2 (rp ≥ 0.68), and BRISQUE and NIQE on T1C (rp ≥ 0.62) images show strong correlation; while to SNRcsf values, BLIINDS-II correlates well on T2 * (rp ≥ 0.63) and T2 (rp ≥ 0.64) weighted MR imagi…”
BackgroundInfluentialPerceptual Quality Assessment for Screen Content Images by Spatial Continuity
Fang, Y., Du, R., Zuo, Y., Wen, W., & Li, L. (2019) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2951747 · Cited by 56
“In this implementation, similar to related studies [12], [17], we randomly divide the image data into training set and testing set for 1000 times.”
MethodInfluentialAttentive Deep Stitching and Quality Assessment for 360$^{\circ }$ Omnidirectional Images
Li, J., Zhao, Y., Ye, W., Yu, K., & Ge, S. (2019) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2019.2953950 · Cited by 56
“evaluations while the NIQE [73] is not sensitive to this kind 626”
BackgroundMethodInfluentialA Residual Diffusion Model for High Perceptual Quality Codec AugmentationPreprint
Goose, N. F., Petersen, J., Wiggers, A., Xu, T., & Sautière, G. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2301.05489 · Cited by 56
“6, we observed little difference in LPIPS on ImageNet-val1k between JPEG+DIRAC-1 and JPEG+DIRAC-100 i.e., between 1 and 100 sampling steps.”
BackgroundMethodInfluentialText2Immersion: Generative Immersive Scene with 3D GaussiansPreprint
Ouyang, H., Heal, K., Lombardi, S., & Sun, T. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2312.09242 · Cited by 56
“To assess the quality of the generated images, we follow the settings established in Text2Nerf [53], which employs BRISQUE [28] and the Natural Image Quality Evaluator (NIQE) [29] to evaluate quality in the absence of a reference image.”
MethodUniversal Rate-Distortion-Perception Representations for Lossy Compression
Zhang, G., Qian, J., Chen, J., & Khisti, A. J. (2025) · IEEE Transactions on Information Theory · doi:10.1109/tit.2025.3584291 · Cited by 55
“No-reference metrics include BRISQUE/NIQE/PIQE [23, 24, 35] and Fréchet Inception Distance [14].”
BacklitNet: A dataset and network for backlit image enhancement
Lv, X., Zhang, S., Liu, Q., Xie, H., Zhong, B., & Zhou, H. (2022) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2022.103403 · Cited by 55
Optimal Transport for Unsupervised Denoising Learning
Wang, W., Wen, F., Yan, Z., & Liu, P. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3170155 · Cited by 56
“It has been shown that perceptual quality is associated with the deviation from natural sample statistics [28], [29], [30], [31], [32], [?].”
BackgroundSemantic-aware Texture-Structure Feature Collaboration for Underwater Image Enhancement
Wang, D., Ma, L., Liu, R., & Fan, X. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9812457 · Cited by 55
No-Reference Image Quality Assessment by Hallucinating Pristine Features
Chen, B., Zhu, L., Kong, C., Zhu, H., Wang, S., & Li, Z. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3205770 · Cited by 55
IRE: Improved Image Super-Resolution Based on Real-ESRGAN
Zhu, Z., Lei, Y., Qin, Y., Zhu, C., & Zhu, Y. (2023) · IEEE Access · doi:10.1109/access.2023.3256086 · Cited by 55
“The NIQE (Natural Image Quality Evaluator) [27] metric was used to evaluate the performance on five test datasets, namely Set5 [28], Set14 [29], BSD100 [30], Urban100 [31], and DIV2K100 [24].”
MethodLet You See in Haze and Sandstorm: Two-in-One Low-Visibility Enhancement Network
Gao, Y., Xu, W., & Lu, Y. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3304668 · Cited by 55
CONVIQT: Contrastive Video Quality Estimator
Madhusudana, P. C., Birkbeck, N., Wang, Y., Adsumilli, B., & Bovik, A. C. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3310344 · Cited by 56
“[29], which uses bandpass DCT coefficients, and BRISQUE [30], NIQE [31], VIIDEO [32] and Dendi et al .”
Self-citationApplying Collaborative Adversarial Learning to Blind Point Cloud Quality Measurement
Wang, J., Gao, W., & Li, G. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3322475 · Cited by 55
“…the known FR and NR methods, including the p2po [22], PSNR-YUV [43], PCQM [31], SSIM [20], MS-SSIM [47], GraphSIM [21], [61], MS-GraphSIM [37], BRISQUE [62], natural image quality evaluator (NIQE) [63], image transferred point cloud quality assessment (IT-PCQA) [51], ResSCNN [64], and PQA-Net [50].”
MethodContent Adaptive Image Detail Enhancement
Kou, F., Chen, W., Li, Z. G., & Wen, C. (2014) · IEEE Signal Processing Letters · doi:10.1109/lsp.2014.2353774 · Cited by 55
“The scores with the metric in [20] of the input and result images are shown in the following table:”
ResultTraining Quality-Aware Filters for No-Reference Image Quality Assessment
Zhang, L., Gu, Z., Liu, X., Li, H., & Lu, J. (2014) · IEEE Multimedia · doi:10.1109/mmul.2014.50 · Cited by 55
Niu, Y., Zhang, H., Guo, W., & Ji, R. (2016) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2016.2634590 · Cited by 55
Predicting the Quality of Images Compressed After Distortion in Two Steps
Yu, X., Bampis, C. G., Gupta, P., & Bovik, A. C. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2922850 · Cited by 46
“Among these, NIQE [24] is a ‘completely blind’, unsuper-”
BackgroundSelf-citationLiang, H., Liu, Y., Sheng, G., & Jiang, X. (2019) · IET Generation Transmission & Distribution · doi:10.1049/iet-gtd.2018.6334 · Cited by 55
Deep Learning Thermal Image Translation for Night Vision Perception
Liu, S., Gao, M., John, V., Liu, Z., & Blasch, E. (2020) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3426239 · Cited by 55
“To evaluate the quality of the colorized CVI images, we apply both NSS-based methods (BIQAA, BLIINDS-II, BRISQUE, and NIQE) and learning-based methods (NIMA and RankIQA).”
MethodInfluentialBilevel Methods for Image Reconstruction
Crockett, C., & Fessler, J. A. (2022) · Foundations and Trends® in Signal Processing · doi:10.1561/2000000111 · Cited by 55
“in natural scenes, typically using some filters [63], [85].”
BackgroundComparison of Despeckle Filters for Breast Ultrasound Images
Zhang, J., Wang, C., & Cheng, Y. (2014) · Circuits Systems and Signal Processing · doi:10.1007/s00034-014-9829-y · Cited by 55
“The result is obtained according to [34], and the patch size was set to 96×96.”
BackgroundMethodHQG-Net: Unpaired Medical Image Enhancement With High-Quality Guidance
He, C., Li, K., Xu, G., Yan, J., Tang, L., Zhang, Y., Wang, Y., & Li, X. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3315307 · Cited by 54
Infrared Thermal Imaging Super-Resolution via Multiscale Spatio-Temporal Feature Fusion Network
Zhang, W., Sui, X., Gu, G., Chen, Q., & Cao, H. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3090021 · Cited by 54
Perceptual Quality Assessment of Omnidirectional Images
Fang, Y., Huang, L., Yan, J., Liu, X., & Liu, Y. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i1.19937 · Cited by 54
“To demonstrate the effectiveness of the proposed models, several state-of-the-art IQA and OIQA models are used for comparison, which can be classified: traditional 2D FR-IQA metrics, i.e. , SSIM (Wang et al. 2004), FSIM (Zhang et al. 2011), VIF (Sheikh and Bovik 2006), VSI (Zhang, Shen, and Li 2014) and DISTS (Ding et…”
Online Video Super-Resolution With Convolutional Kernel Bypass Grafts
Xiao, J., Jiang, X., Zheng, N., Yang, H., Yang, Y., Yang, Y., Li, D., & Lam, K. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3243615 · Cited by 54
“Since this dataset does not provide the ground-truth videos, we compared our proposed CKBG with EDSR, RRN, RLSP, and BasicVSR ∗ in terms of the nonreference quality measures, i.e., BRISQUE [56] and NIQE [57].”
MethodTask-Specific Normalization for Continual Learning of Blind Image Quality Models
Zhang, W., Ma, K., Zhai, G., & Yang, X. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3371349 · Cited by 54
“Many early BIQA methods are based on hand-engineered natural scene statistics (NSS) in spatial [6], [16], transformed [17], or both domains [18].”
MethodA Self-Supervised CNN for Image Watermark Removal
Tian, C., Zheng, M., Jiao, T., Zuo, W., Zhang, Y., & Lin, C. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3375831 · Cited by 54
“To fairly test quality of obtained images from our SWCNN, we choose blind image quality evaluators with popular codes, i.e., NIQE [41] and (ILNIQE) [42] to test comparative experiments in TABLE VI.”
MethodA Conditional Diffusion Model With Fast Sampling Strategy for Remote Sensing Image Super-Resolution
Meng, F., Chen, Y., Jing, H., Zhang, L., Yan, Y., Ren, Y., Wu, S., Feng, T., Liu, R., & Du, Z. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3458009 · Cited by 54
“For real-world SR results without ground-truth images as references, we also adopt no-reference image evaluation metrics recently used in some RSI SR studies [20], [54], such as entropy [55] and natural image quality evaluator (NIQE) [56].”
MethodHarnessing Diffusion-Yielded Score Priors for Image Restoration
Lin, X., Yu, F., Hu, J., You, Z., Shi, W., Ren, J., Gu, J., & Dong, C. (2025) · ACM Transactions on Graphics · doi:10.1145/3763346 · Cited by 55
Objective Quality Assessment of Interpolated Natural Images
Yeganeh, H., Rostami, M. G., & Wang, Z. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2456638 · Cited by 54
“Therefore, in addition to comparing the proposed IND and WIND measures with an average human subject (as described earlier), we compare them with well-known FR-IQA measures, including PSNR and SSIM [16].”
MethodUtilizing Image Scales Towards Totally Training Free Blind Image Quality Assessment
Saha, A., & Wu, Q. M. J. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2411436 · Cited by 54
“Some recent approaches [24], [25] work without training on human scores as well on distorted images.”
BackgroundMethodInfluentialHepp, T., Wortner, P., Schönhals, A., & Gipp, B. (2018) · Workshop on Cryptocurrencies and Blockchains for Distributed Systems (CryBlock) · doi:10.1145/3211933.3211944 · Cited by 54
Effects of Compression on Remote Sensing Image Classification Based on Fractal Analysis
Chen, Z., Hu, Y., & Zhang, Y. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2019.2891679 · Cited by 54
“Similar to [35], we also characterize the mean subtracted contrast normalized (MSCN) coefficients distribution of the stretched FD map and its corresponding original image using”
Accurate and Efficient Image Super-Resolution via Global-Local Adjusting Dense Network
Zhang, X., Gao, P., Liu, S., Zhao, K., Li, G., Yin, L., & Chen, C. W. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.3005025 · Cited by 54
Full-Resolution Quality Assessment for Pansharpening
Scarpa, G., & Ciotola, M. (2022) · Remote Sensing · doi:10.3390/rs14081808 · Cited by 54
“It is also worth to mention other no-reference quality indexes, such as the Natural Image Quality Evaluator (NIQE) [50, 36] that seeks to assess the image quality by-itself rather than checking consistency.”
BackgroundComparative Perceptual Assessment of Visual Signals Using Free Energy Features
Zhai, G., Zhu, Y., & Min, X. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.3029891 · Cited by 54
Study of the Subjective and Objective Quality of High Motion Live Streaming Videos
Shang, Z., Ebenezer, J. P., Wu, Y., Wei, H., Sethuraman, S., & Bovik, A. C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3136723 · Cited by 54
“The NR VQA algorithms that were tested include NIQE [54], BRISQUE [55], HI-GRADE [56], CORNIA [57], TLVQM [58], V-BLIINDS [59], and ChipQA [60], [61].”
MethodSelf-citationDual Learning-Based Graph Neural Network for Remote Sensing Image Super-Resolution
Liu, Z., Feng, R., Wang, L., Han, W., & Zeng, T. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3199750 · Cited by 54
“8 quality evaluation indexes, Natural Image Quality Evaluator (NIQE) [59], and Perceptual Index (PI) [60], are used to compare better.”
MethodSingle image super‐resolution based on progressive fusion of orientation‐aware features
He, Z., Chen, D., Cao, Y., Yang, J., Cao, Y., Li, X. S., Tang, S., Zhuang, Y., & Lu, Z. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.109038 · Cited by 54
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.