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 501–600 of 1,013
RankSRGAN: Super Resolution Generative Adversarial Networks With Learning to Rank
Zhang, W., Liu, Y., Dong, C., & Qiao, Y. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3096327 · Cited by 83
“Inspired by PIRM2018-SR Challenge[20], we adopt NIQE[21] as the perceptual metric.”
BackgroundMethodInfluentialSahu, G., Seal, A., Jaworek-Korjakowska, J., & Krejcar, O. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3271753 · Cited by 83
“…quality assessment metrics are Blind/Referenceless Image Spatial QUality Evaluator (BRISQUE) [56], natural image quality evaluator (NIQE) [57], entropy (E) [5], spatial–spectral entropy-based quality (SSEQ) [58], and entropy-based no-TABLE reference image quality assessment (ENIQA) [59]…”
BackgroundSingle image super-resolution: a comprehensive review and recent insight
Al‐Mekhlafi, H., & Liu, S. (2023) · Frontiers of Computer Science · doi:10.1007/s11704-023-2588-9 · Cited by 83
Huang, Z., Zhang, Y., Li, Q., Li, Z., Zhang, T., Sang, N., & Xiong, S. (2019) · International Journal of Remote Sensing · doi:10.1080/01431161.2019.1580821 · Cited by 83
“For the real-life experiments, noise reduction (NR) (Bouali and Ladjal 2011) to assess the destriping performance, Q-Metric (Chang et al. 2014) to evaluate the denoising performance, and natural image quality evaluator (NIQE) (Mittal, Soundararajan, and Bovik 2013; Huang et al. 2018a), are employed to evaluate the imp…”
MethodInfluentialLow-Light Image Enhancement via Self-Reinforced Retinex Projection Model
Ma, L., Liu, R., Wang, Y., Fan, X., & Luo, Z. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3162493 · Cited by 82
“Obviously, our method reached the lowest NIQE values of all benchmarks in most cases, which adequately demonstrates the excellent naturalness of the enhanced results obtained by our proposed SRRP. Fig.”
BackgroundRCDNet: An Interpretable Rain Convolutional Dictionary Network for Single Image Deraining
Wang, H., Xie, Q., Zhao, Q., Li, Y., Liang, Y. Q., Zheng, Y., & Meng, D. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3231453 · Cited by 83
“NIQE and BRISQUE aim to quantify the quality of a distorted image in a way that matches the human judgments of visual quality as closely as possible.”
BackgroundInfluentialMuLA-GAN: Multi-Level Attention GAN for Enhanced Underwater Visibility
Bakht, A. B., Jia, Z., Din, M. U., Akram, W., Saoud, L. S., Seneviratne, L. D., Lin, D., He, S., & Hussain, I. (2024) · Ecological Informatics · doi:10.1016/j.ecoinf.2024.102631 · Cited by 84
SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration
Wang, J., Lin, Z., Wei, M., Zhao, Y., Yang, C., Loy, C. C., & Jiang, L. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00207 · Cited by 83
“For synthetic datasets with LQ-HQ pairs, we employ full-reference metrics such as PSNR, SSIM, LPIPS [76], and DISTS [16], and no-reference metrics including NIQE [37], CLIP-IQA [53], MUSIQ [26], and DOVER [59].”
Fuzzy Logic-Based Histogram Equalization for Image Contrast Enhancement
Magudeeswaran, V., & Ravichandran, C. G. (2013) · Mathematical Problems in Engineering · doi:10.1155/2013/891864 · Cited by 82
Low-light image enhancement of high-speed endoscopic videos using a convolutional neural network
Gómez, P., Semmler, M., Schützenberger, A., Bohr, C., & Döllinger, M. (2019) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-019-01965-4 · Cited by 83
Blind Image Quality Assessment by Natural Scene Statistics and Perceptual Characteristics
Liu, Y., Gu, K., Li, X., & Zhang, Y. (2020) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3414837 · Cited by 82
“The criteria of patch selection we use here is that the patch whose variance exceeds a threshold will be selected, as adopted in Reference [26].”
BackgroundMethodInfluentialA Hitchhiker’s Guide to Structural Similarity
Venkataramanan, A. K., Wu, C., Bovik, A. C., Katsavounidis, I. X., & Shahid, Z. (2021) · IEEE Access · doi:10.1109/access.2021.3056504 · Cited by 81
“For encoding applications where the source video to be encoded is already impaired by some distortion(s), e.g. UGC, as is often found on sites like YouTube, Facebook, and Instagram, SSIM and NIQE can be combined via a 2-step assessment process to produce significantly improved encode quality predictions [35], [36].”
MethodSelf-citationSeo, S., Ki, S., & Kim, M. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.3030895 · Cited by 81
“For more sophisticated modeling, natural image quality evaluator (NIQE) [57] extracts features based on a multivariate Gaussian model and relates them to perceived quality in an unsupervised manner.”
BackgroundSahu, G., Seal, A., Bhattacharjee, D., Frischer, R., & Krejcar, O. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3225797 · Cited by 81
“…SIMilarity Index (FSIM) [68] and four no-reference quality assessment metrics are Blind/Referenceless image spatial quality evaluator (BRISQUE) [69], natural image quality evaluator (NIQE) [70], contrast enhancement based contrast-changed image quality measure (CEIQ) [71] and entropy (E) [65].”
BackgroundEnd-to-End Alternating Optimization for Real-World Blind Super Resolution
Luo, Z., Huang, Y., Li, S., Wang, L., & Tan, T. N. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-023-01833-7 · Cited by 81
“NIQE (Mittal et al., 2012), NRQM (Ma et al., 2017), and PI (Blau et al., 2018) are used.”
MethodPerceptually optimized image rendering
Laparra, V., Berardino, A., Ballé, J., & Simoncelli, E. P. (2017) · Journal of the Optical Society of America A · doi:10.1364/josaa.34.001511 · Cited by 81
Ghani, A. S. A. (2018) · Ocean Engineering · doi:10.1016/j.oceaneng.2018.05.027 · Cited by 81
GAN-Based Image Super-Resolution with a Novel Quality Loss
Zhu, X., Zhang, L., Zhang, L., Liu, X., Shen, Y., & Zhao, S. (2020) · Mathematical Problems in Engineering · doi:10.1155/2020/5217429 · Cited by 81
Wang, J., Duan, H., Liu, J., Chen, S., Min, X., & Zhai, G. (2024) · Lecture Notes in Computer Science · doi:10.1007/978-981-99-9119-8_5 · Cited by 80
Dong, R., Mou, L., Zhang, L., Fu, H., & Zhu, X. X. (2022) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2022.07.010 · Cited by 81
USCFormer: Unified Transformer With Semantically Contrastive Learning for Image Dehazing
Wang, Y., Xiong, J., Yan, X., & Wei, M. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3277709 · Cited by 80
From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal
Guo, Y., Xiao, X., Chang, Y., Deng, S., & Yan, L. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01111 · Cited by 80
Underwater Image Quality Assessment: Benchmark Database and Objective Method
Liu, Y., Zhang, B., Hu, R., Gu, K., Zhai, G., & Dong, J. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3371218 · Cited by 80
“…with nineteen state-of-the-art IQA and UIQA metrics, including CNN-IQA [50], WaDIQaM-NR [51], DBCNN [52], HyperIQA [53], TReS [54], BRISQUE [55], UNIQUE [56], DipIQ [57], NIQE [58], SNP-NIQE [3], NPQI [10], CCF [15], UCIQE [13], URQ [32], FDUM [35], UIQM [17], UIQI [36], UEIQM [30], and GLCQE [37].”
MethodNo-reference quality assessment of deblocked images
Li, L., Zhou, Y., Lin, W., Wu, J., Zhang, X., & Chen, B. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.11.063 · Cited by 79
A novel multi-scale fusion framework for detail-preserving low-light image enhancement
Xu, Y., Yang, C., Sun, B., Yan, X., & Chen, M. (2020) · Information Sciences · doi:10.1016/j.ins.2020.09.066 · Cited by 79
Li, S., Ren, W., Wang, F., Araujo, I. B., Tokuda, E. K., Hirata, R., Junior, R. M. C., Wang, Z., & Cao, X. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01416-w · Cited by 79
Shi, Y., Han, L., Han, L., Chang, S., Hu, T., & Dancey, D. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3193441 · Cited by 80
“The PI is defined by two non-referenced image quality measurements, MA [62] and NIQE [63], described as: PI(Ihr, Isr) = 1 2 ((10−MA(Ihr, Isr))) +NIQE(Ihr, Isr) (16) In order to measure the spectral distortion, the spectral angle mapper(SAM), was used to calculate the average angle between a super-resolution HSI and it…”
Deep Learning for Downscaling Remote Sensing Images: Fusion and super-resolution
Sdraka, M., Papoutsis, I., Psomas, B., Vlachos, K., Ioannidis, K., Karantzalos, K. G., Gialampoukidis, I., & Vrochidis, S. (2022) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2022.3171836 · Cited by 79
“The SNR based on contrast pyramid variations FR Feature similarity index (FSIM) [44] [0, 1] Similar to the SSIM and utilizes phase congruency and gradient magnitude FR Gradient similarity measure (GSM) [45] [0, 1] Similar to the SSIM and measures gradient similarity FR Spectral angle mapper (SAM) [46] [ , ]0 r Compare…”
MethodBrightness-Based Convolutional Neural Network for Thermal Image Enhancement
Lee, K., Lee, J., Lee, J., Hwang, S., & Lee, S. (2017) · IEEE Access · doi:10.1109/access.2017.2769687 · Cited by 78
“…evaluate the thermal image enhancement performance, seven image quality metrics were used: the PSNR, SSIM [28], and IFC [29] for full-reference quality assessment using the TIRset26; NIQE [30], NPBM [31], CV [32], and UID [32] for no-reference quality assessment using the KAIST Dataset [42].”
BackgroundMethodStructure-Texture Aware Network for Low-Light Image Enhancement
Xu, K., Chen, H., Xu, C., Jin, Y., & Zhu, C. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3141578 · Cited by 78
Image dehazing via enhancement, restoration, and fusion: A survey
Guo, X., Yang, Y., Wang, C., & Ma, J. (2022) · Information Fusion · doi:10.1016/j.inffus.2022.07.005 · Cited by 78
A Dual-Channel Dehaze-Net for Single Image Dehazing in Visual Internet of Things Using PYNQ-Z2 Board
Sahu, G., Seal, A., Yazidi, A., & Krejcar, O. (2022) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2022.3217801 · Cited by 79
“BRISQUE and NIQE quantify the amount of naturalness in the dehazed image [63], [64].”
BackgroundGraph-Represented Distribution Similarity Index for Full-Reference Image Quality Assessment
Shen, W., Zhou, M., Luo, J. T., Li, Z. G., & Kwong, S. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3390565 · Cited by 78
“…assess the performances of several representative no-reference and full-reference PCQA methods, namely, the natural image quality evaluator (NIQE) [75], the blind/referenceless image spatial quality evaluator (BRISQUE) [4], 3DQA [76], point-to-point (p2point) [77] and point-to-plane (p2plane)…”
BackgroundChen, W., Shen, L., Lin, J., Luo, J., Li, X., & Yuan, Y. (2024) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2024.acl-long.514 · Cited by 78
“We assess CXR-to-report generation using BLEU (B), METEOR (M), and ROUGE-L (R-L) (Chen et al., 2020b), and report-to-CXR generation using FID (Heusel et al., 2017) and NIQE (Mittal et al., 2012).”
No-reference/Blind Image Quality Assessment: A Survey
Xu, S., Jiang, S., & Min, W. (2016) · IETE Technical Review · doi:10.1080/02564602.2016.1151385 · Cited by 79
“In [88], a completely blind NR-IQA algorithm called natural image quality evaluator (NIQE), which does not require learning from subjectively evaluated images and only makes use of measurable deviations from statistical regularities observed in natural images, was proposed.”
BackgroundMethodInfluentialCombining Local and Global Measures for DIBR-Synthesized Image Quality Evaluation
Yue, G., Hou, C., Gu, K., Zhou, T., & Zhai, G. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2875913 · Cited by 78
“(g) NIQE [60], (0.”
BackgroundDeep Proximal Unrolling: Algorithmic Framework, Convergence Analysis and Applications
Liu, R., Cheng, S., Ma, L., Fan, X., & Luo, Z. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2913536 · Cited by 78
“Following most existing works, Natural Image Quality Evaluator (NIQE) [52] is set as our quantitative metric which derived from statistical regularites observed in natural images.”
BackgroundReti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model
He, C., Fang, C., Zhang, Y., Tian, Y., Li, K., Tang, L., Guo, Z., Li, X., & Farsiu, S. (2023) · International Conference on Learning Representations · doi:10.48550/arxiv.2311.11638 · Cited by 78
“7, our Reti-Diff exhibits a substantial advantage over existing methods, as evidenced by higher average precision (AP) scores.”
Blind visual quality assessment for image super-resolution by convolutional neural network
Fang, Y., Zhang, C., Yang, W., Liu, J., & Guo, Z. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-5805-z · Cited by 77
“However, the visual distortion generated from image Table 2 Performance evaluation of the proposed method Models PSNR SSIM MSSSIM BRISQUE ILNIQE NIQE QAC NRSL Ours PLCC 0.3335 0.5726 0.6218 0.6176 0.6198 0.6364 0.4704 0.8011 0.9156 SRCC 0.3110 0.5562 0.6452 0.5723 0.6282 0.6254 0.4938 0.6874 0.8394 RMSE 2.9383 1.798 1…”
MethodInfluentialShin, J., Kim, M., Paik, J., & Lee, S. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2922127 · Cited by 77
“To measure the visual quality in our real-world haze data, we employed the contrast-to-noise ratio (CNR) [55], entropy [53], the natural image quality evaluation (NIQE) method [56], the percentage of saturated pixels [57], and the subjective user study [8].”
MethodQuality Assessment of Image Super-Resolution: Balancing Deterministic and Statistical Fidelity
Zhou, W., & Wang, Z. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3547899 · Cited by 78
“NR methods may be derived from the natural scene statistics (NSS) models, and the notable ones include the blind/referenceless image spatial quality evaluator (BRISQUE) [15], the natural image quality evaluator (NIQE) [16], the blind image integrity notator using DCT statistics (BLIINDSII) [21], and the distortion ide…”
MethodKorkmaz, C., Tekalp, A. M., & Doğan, 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/cvpr52733.2024.00566 · Cited by 77
“The perceptual quality of images is assessed via utilizing the full-reference metrics LPIPS [65], DISTS [10], and no-reference metrics NIQE [44], NRQM [39] and PI [4] on RGB images for a comprehensive evaluation.”
Frequency domain-based latent diffusion model for underwater image enhancement
Song, J., Xu, H., Jiang, G., Yu, M., Chen, Y., Luo, T., & Song, Y. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.111198 · Cited by 77
Blind Quality Assessment of Camera Images Based on Low-Level and High-Level Statistical Features
Liu, Y., Gu, K., Wang, S., Zhao, D., & Gao, W. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2849602 · Cited by 77
“The other one category is training-free, which includes SISBLIM, LPSI, NIQE, ILNIQE, QAC and BIQME.”
BackgroundMethodInfluentialBahat, Y., & Michaeli, T. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00279 · Cited by 76
A switched view of Retinex: Deep self-regularized low-light image enhancement
Jiang, Z., Li, H., Liu, L., Men, A., & Wang, H. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.05.025 · Cited by 76
Enlighten-GAN for Super Resolution Reconstruction in Mid-Resolution Remote Sensing Images
Gong, Y., Liao, P., Zhang, X., Zhang, L., Chen, G., Zhu, K., Tan, X., & Lv, Z. (2021) · Remote Sensing · doi:10.3390/rs13061104 · Cited by 76
“It is formed as PI = 0.5× ((10−Ma) + NIQE) (5) where a lower PI implies a richer texture.”
BackgroundInfluentialGuo, Y., Lu, Y., & Liu, R. W. (2021) · Journal of Navigation · doi:10.1017/s0373463321000783 · Cited by 76
“• NIQE: Natural image quality evaluator (Mittal et al., 2013) is proposed according to the statistical law observed in natural images.”
BackgroundZhang, J., Zhou, X., Li, L., Hu, T., & Chen, F. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3196050 · Cited by 76
Xue, X., Li, Z., Ma, L., Jia, Q., Liu, R., & Fan, X. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.109041 · Cited by 76
Underwater image quality optimization: Researches, challenges, and future trends
Wang, M., Zhang, K., Wei, H., Chen, W., & Zhao, T. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.104995 · Cited by 76
A degradation-aware guided fusion network for infrared and visible image
Wang, X., Guan, Z., Qian, W., Cao, J., Ma, R., & Bi, C. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.102931 · Cited by 76
A Progressively Enhanced Network for Video Satellite Imagery Superresolution
Jiang, K., Wang, Z., Yi, P., & Jiang, J. (2018) · IEEE Signal Processing Letters · doi:10.1109/lsp.2018.2870536 · Cited by 76
“In addition, because the test images have no reference objects (i.e., using the observed LR images instead of the downscaled LR images as input), we provide the visual results and introduce the indicators of average gradient (AG) [31] and naturalness image quality evaluator (NIQE) [32] to evaluate the reconstruction q…”
MethodInfluentialProgressive perception-oriented network for single image super-resolution
Zheng, H., Li, J., Gao, X., & Wang, X. (2020) · Information Sciences · doi:10.1016/j.ins.2020.08.114 · Cited by 75
Liu, X., Pedersen, M., & Wang, R. (2022) · Digital Signal Processing · doi:10.1016/j.dsp.2022.103547 · Cited by 75
Generative Artificial Intelligence Meets Synthetic Aperture Radar: A survey
Huang, Z., Zhang, X., Tang, Z., Xu, F., Datcu, M. P., & Han, J. (2024) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2024.3483459 · Cited by 76
“The NR models mainly rely on the image quality benchmark datasets that record the evaluation results of human beings for visual perception [298], [299], [300], [301].”
Guided Real Image Dehazing Using YCbCr Color Space
Fang, W., Fan, J., Zheng, Y., Weng, J., Tai, Y. Y., & Li, J. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i3.32297 · Cited by 75
LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation
Yang, S., Tan, J., Zhang, M., Wu, T., Wetzstein, G., Liu, Z., & Lin, D. (2025) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/3721238.3730643 · Cited by 75
Low-Light Image Enhancement via CLIP-Fourier Guided Wavelet Diffusion
Xue, M., He, J., Wang, W., & Zhou, M. (2025) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3764933 · Cited by 75
“Subsequently, the enhanced three high-frequency subbands { ˆ 𝑉 𝐾𝐿 , ˆ 𝐻 𝐾𝐿 , ˆ 𝐷 𝐾𝐿 } are obtained by dilation convolutions [7] and depth-wise separable convolutions.”
Despeckling of clinical ultrasound images using deep residual learning
Kokil, P., & Sudharson, S. (2020) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2020.105477 · Cited by 75
KonVid-150k: A Dataset for No-Reference Video Quality Assessment of Videos in-the-Wild
Götz-Hahn, F., Hosu, V., Lin, H., & Saupe, D. (2021) · IEEE Access · doi:10.1109/access.2021.3077642 · Cited by 76
“…natural scene statistics (NSS) [49] being the predominant hypothesis used in several works, such as the naturalness image quality evaluator (NIQE) [50], blind/referenceless image spatial quality evaluator (BRISQUE) [51], feature-map-based refer-enceless image quality evaluation engine (FRIQUEE)…”
MethodBiologically Inspired Blind Quality Assessment of Tone-Mapped Images
Yue, G., Hou, C., Gu, K., Mao, S., & Zhang, W. (2017) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2017.2739708 · Cited by 74
“The selected NR IQA methods compose of opinion-unaware methods, including NIQE [12] and ILNIQE [13], and opinion-aware methods, including BIQI [14], HOSA [42], FISH [43], BLIINDS2 [15], BRISQUE [37], GM-LOG [16], SISLBM [44], SSEQ [38], TCLT [45], NFERM [18], NRSL [19], and BSD [17].”
BackgroundMethodA No-Reference Evaluation Metric for Low-Light Image Enhancement
Zhang, Z., Sun, W., Min, X., Zhu, W., Wang, T., Lu, W., & Zhai, G. (2021) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme51207.2021.9428312 · Cited by 74
“NIQE [10] employs measurable deviations from statistical regularities observed in natural images for image quality evaluation.”
MethodIDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-Sensing Images
Wang, M., Song, Y., Wei, P., Xian, X., Shi, Y., & Lin, L. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3378720 · Cited by 74
“The no-reference metrics used in our evaluation include natural image quality evaluator (NIQE) [57], multidimension attention network for no-reference image quality assessment (MANIQA) [58], BRISQUE [59], and perceptual index (PI) [60].”
MethodSeeing Motion at Nighttime with an Event Camera
Liu, H., Peng, S., Zhu, L., Chang, Y., Zhou, H., & Yan, L. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.02423 · Cited by 74
“No-reference metrics such as LOE [74], NIQE [75], and SPAQ [76] are adopted for evaluation.”
Speckle filtering of medical ultrasonic images using wavelet and guided filter
Zhang, J., Lin, G., Wu, L., & Cheng, Y. (2015) · Ultrasonics · doi:10.1016/j.ultras.2015.10.005 · Cited by 74
Visual Importance and Distortion Guided Deep Image Quality Assessment Framework
Guan, J., Yi, S., Zeng, X., Cham, W.-K., & Wang, X. (2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2703148 · Cited by 74
“Results of IDEAL [33], QAC [49] and IL-NIQE [57] are calculated by the source code released by the authors.”
BackgroundAVT-VQDB-UHD-1: A Large Scale Video Quality Database for UHD-1
Rao, R. R. R., Göring, S., Robitza, W., Feiten, B., & Raake, A. (2019) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism46123.2019.00012 · Cited by 74
“This paper provides such an open accessible UHD dataset containing subjective scores, features such as BRISQUE [24], NIQE [23], per-frame VMAF scores and other such models, where realistic resolutions and bandwidth conditions for DASH were considered.”
MethodNo-reference Stereoscopic Image Quality Assessment Using Natural Scene Statistics
Appina, B., Khan, S., & Channappayya, S. S. (2016) · Signal Processing Image Communication · doi:10.1016/j.image.2016.02.001 · Cited by 73
“Our approach is inspired by the success of applying natural scene statistics (NSS) to all the classes of 2D IQA algorithms – FR, RR [8], and NR [9, 10, 11, 12] methods.”
MethodInfluentialZhou, Y., Li, L., Wang, S., Wu, J., Fang, Y., & Gao, X. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2912463 · Cited by 73
“rics, including BIQI [54], BLIINDS [55], BRISQUE [56], DESQUE [57], DIIVINE [39], NIQE [58], QAC [59], ILNIQE [60], NFERM [61], and M3 [62].”
Lee, R., Venieris, S. I., & Lane, N. D. (2021) · ACM Computing Surveys · doi:10.1145/3469094 · Cited by 73
“…using either i) a distortion-based metric, such as Peak Signal-to-Noise Ratio (PSNR) [44] or Structural Similarity Index Measure (SSIM) [155], or ii) a perceptual-based metric, such as Naturalness Image Quality Evaluator (NIQE) [117] or Learned Perceptual Image Patch Similarity (LPIPS) [174].”
BackgroundMethodUnpaired Learning for Deep Image Deraining with Rain Direction Regularizer
Liu, Y., Yue, Z., Pan, J., & Su, Z. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00471 · Cited by 73
Vijayalakshmi, D., & Nath, M. K. (2022) · Digital Signal Processing · doi:10.1016/j.dsp.2022.103532 · Cited by 73
Metric Learning Based Interactive Modulation for Real-World Super-Resolution
Mou, C., Wu, Y., Wang, X., Dong, C., Zhang, J., & Shan, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19790-1_43 · Cited by 73
Blind Face Restoration via Integrating Face Shape and Generative Priors
Zhu, F., Zhu, J., Chu, W., Zhang, X., Ji, X., Wang, C., & Tai, Y. 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/cvpr52688.2022.00751 · Cited by 73
“FID [14] and NIQE [33] are adopted as the non-reference perceptual metrics.”
MethodPixel-Wise Gamma Correction Mapping for Low-Light Image Enhancement
Li, X., Liu, M., & Ling, Q. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3286802 · Cited by 74
“Two no-reference metrics, including NIQE [64] and BRISQUE [65], and three full-reference metrics, including PSNR, SSIM [66], and LPIPS [67], are adopted to measure the enhancement quality.”
MethodAIGC Image Quality Assessment via Image-Prompt Correspondence
Peng, F., Fu, H., Ming, A., Wang, C., Ma, H., He, S., Dou, Z., & Chen, S. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00644 · Cited by 73
Evagaussians: Event Stream Assisted Gaussian Splatting from Blurry Images
Yu, W., Feng, C., Li, J., Tang, J., Yang, J., Tang, Z., Cao, M., Jia, X., Yang, Y., Yuan, L., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02298 · Cited by 73
“…datasets, since the sharp ground-truth images are unavailable, we utilize several No-Reference Image Quality Assessment (NR-IQA) metrics for evaluation, including BRISQUE [31], NIQE [32], PIQE [53], RankIQA [26], and MetaIQA [73], which allow for image evaluation when lacking ground truth images.”
Blind Quality Assessment of Tone-Mapped Images Considering Colorfulness, Naturalness, and Structure
Yue, G., Hou, C., & Zhou, T. (2018) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2018.2851984 · Cited by 73
“The first type contains those methods designed for natural scene images, including NIQE [33], ILNIQE [34], BRISQUE [24], SSEQ [29], NFERM [23], NRSL [28], and BSD [27].”
BackgroundMethodUnsupervised Low-Light Image Enhancement via Histogram Equalization PriorPreprint
Zhang, F. S., Shao, Y., Sun, Y., Zhu, K., Gao, C., & Sang, N. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.01766 · Cited by 73
“Best viewed in color and by zooming in. method with the state-of-the-art methods (include supervised and unsupervised methods), we use traditional metrics to evaluate, such as Peak-Signal-Noise-Rate (PSNR), Structural Similarity (SSIM) [35], and Natural Image Quality Evaluator (NIQE) [36].”
MethodFeng, X., Zhang, W., Su, X., & Xu, Z. (2021) · Remote Sensing · doi:10.3390/rs13091858 · Cited by 72
“The lower perceptual index means a better reconstructed image. perceptual index = 1 2 (( 10−Ma′s score ) + NIQE ) (10) The result between our RRDGAN with VGG loss (RRDGAN-VGG) as its discriminator and RRDGAN with MSE loss (RRDGAN-MSE) as its discriminator were also compared int this table.”
MethodLin, Y.-H., & Lu, Y.-C. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3189805 · Cited by 72
Reduced-Reference Quality Assessment of Point Clouds via Content-Oriented Saliency Projection
Zhou, W., Yue, G., Zhang, R., Qin, Y., & Liu, H. (2023) · IEEE Signal Processing Letters · doi:10.1109/lsp.2023.3264105 · Cited by 72
“The compared image-based metrics involve PNSR, SSIM [16], BRISQUE [23], and NIQE [24].”
MethodAnalysis of Video Quality Datasets via Design of Minimalistic Video Quality Models
Sun, W., Wen, W., Min, X., Lan, L., Zhai, G., & Ma, K. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3385364 · Cited by 72
“A density-based fair sampling strategy was used to select 1,200 videos with the resolution of 960 × 540 from YFCC100M [38] based on six attributes: blur, colorfulness, contrast, spatial information, temporal information, and predicted video quality by V-NIQE [39].”
MethodEficient image denoising using deep learning: A brief survey
Jiang, B., Li, J., Lu, Y., Cai, Q., Song, H., & Lu, G. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103013 · Cited by 75
Low-Light Image Enhancement via Generative Perceptual Priors
Zhou, H., Dong, W., Liu, X., Zhang, Y., Zhai, G., & Chen, J. (2025) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v39i10.33168 · Cited by 72
Lan, X., Xian, W., Zhou, M., Yan, J., Wei, X., Luo, J., Jia, W., & Kwong, S. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3586106 · Cited by 72
“Mittal et al. [35] introduced a method called the natural image quality evaluator (NIQE), which does not require training on distorted images.”
Learning a Continuous-Time Streaming Video QoE Model
Ghadiyaram, D., Pan, J., & Bovik, A. C. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2790347 · Cited by 72
“Multi-learner Stall only Inputs + Scene Criticality NIQE [30] 0.”
BackgroundMethodInfluentialSelf-citationAnalyzing Perception-Distortion Tradeoff Using Enhanced Perceptual Super-Resolution Network
Vasu, S., Madam, N. T., & Rajagopalan, A. N. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-11021-5_8 · Cited by 72
Effective and Efficient Photo-Based PM2.5 Concentration Estimation
Yue, G., Gu, K., & Qiao, J. (2019) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2018.2886091 · Cited by 72
“The first category contains three lately designed methods for characterizing image naturalness, such as NIQE [38], IL-NIQE [39], and LPSI [40].”
MethodSinDDM: A Single Image Denoising Diffusion ModelPreprint
Kulikov, V., Yadin, S., Kleiner, M., & Michaeli, T. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2211.16582 · Cited by 72
“At the same time, our samples have comparable quality to those of the competing meth-ods, as ranked by the no-reference image quality measures NIQE (Mittal et al., 2012), NIMA (Talebi & Milanfar, 2018) and MUSIQ (Ke et al., 2021).”
ResultDeepInverse: A Python package for solving imaging inverse problems with deep learning
Tachella, J. A., Terris, M., Hurault, S., Wang, A., Davy, L., Scanvic, J., Sechaud, V., Vo, R., Moreau, T., Davies, T., et al. (2025) · The Journal of Open Source Software · doi:10.21105/joss.08923 · Cited by 73
“…trade-off in image reconstruction problems [78], the library provides common popular distortion metrics such as PSNR, SSIM [79], and LPIPS [80], as well as no-reference perceptual metrics such as NIQE [81] and QNR [82], which can be used to evaluate the quality of the reconstructions.”
Barman, N., Jammeh, E., Ghorashi, S. A., & Martini, M. G. (2019) · IEEE Access · doi:10.1109/access.2019.2920477 · Cited by 71
“Most of the IQA and VQA metrics, such as Blind Image Quality Index (BIQI) [9], Natural Image Quality Evaluator (NIQE) [10] and Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) [11]) are designed taking into account statistics or properties which are inherent to natural images.”
BackgroundInfluentialA Comparative Evaluation Of Temporal Pooling Methods For Blind Video Quality Assessment
Tu, Z., Chen, C.-J., Chen, L.-H., Birkbeck, N., Adsumilli, B., & Bovik, A. C. (2020) · 2020 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip40778.2020.9191169 · Cited by 71
“We selected five popular NR IQA models: NIQE [27], BRISQUE [4], GM-LOG [38], HIGRADE [39], and CORNIA [40], as frame-level quality predictors, and evaluated the temporal pooling methods on two recent large scale UGC VQA databases: KoNViD-1k [34] and LIVE-VQC [35].”
BackgroundMethodSelf-citationHan, J., Li, W., Fang, P., Sun, C., Hong, J., Armin, M. A., Petersson, L., & Li, H. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-19797-0_13 · Cited by 72
Zhang, X., Wang, X., Yan, C., & Sun, Q. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3346886 · Cited by 71
“To quantitatively evaluate different algorithms, we employ six evaluation metrics, which are visual information fidelity (VIF), average gradient (AG), entropy (EN), spatial frequency (SF), natural image quality evaluator (NIQE) [52], and color quality enhancement (CQE) [53].”
MethodDenoising diffusion post-processing for low-light image enhancement
Panagiotou, S., & Bosman, A. S. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110799 · Cited by 72
“For the unpaired test data we adopt the following no-reference metrics: natural image quality evaluator (NIQE) [55], blind/referenceless image spatial quality evaluator (BRISQUE) [56] and the smartphone photography attribute and quality (SPAQ) database [57].”
MethodStudy of Subjective and Objective Naturalness Assessment of AI-Generated Images
Chen, Z., Sun, W., Wu, H., Zhang, Z., Jia, J., Huang, R., Min, X., Zhai, G., & Zhang, W. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3509032 · Cited by 71
“…Methods: We select 14 representative meth-ods for comparison, including two classical no reference (NR) IQA methods: BRISQUE [88] and NIQE [89], five deep NR IQA methods, DBCNN [90], HyperIQA [91], MUSIQ [92], UNIQUE [93], and MANIQA [94], four image aesthetic assessment (IAA) methods:…”
Blind Image Quality Assessment by Learning from Multiple Annotators
Ma, K., Liu, X., Fang, Y., & Simoncelli, E. P. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803390 · Cited by 71
“To generate training labels, we used six full-reference IQA models: SSIM [1], MS-SSIM [23], VIF [24], MAD [12], VSI [25] and NLPD [26]; and three BIQA models: NIQE [27], ILNIQE [28] and dipIQ [9].”
MethodBidirectional Convolutional LSTM Neural Network for Remote Sensing Image Super-Resolution
Chang, Y., & Luo, B. (2019) · Remote Sensing · doi:10.3390/rs11202333 · Cited by 71
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.