The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index; none of the 14 sources its claims cite is checked for support yet.
Multiscale structural similarity for image quality assessment
Abstract
The structural similarity image quality paradigm is based on the assumption that the human visual system is highly adapted for extracting structural information from the scene, and therefore a measure of structural similarity can provide a good approximation to perceived image quality. This paper proposes a multiscale structural similarity method, which supplies more flexibility than previous single-scale methods in incorporating the variations of viewing conditions. We develop an image synthesis method to calibrate the parameters that define the relative importance of different scales. Experimental comparisons demonstrate the effectiveness of the proposed method.
Overview
CoChat Summary
TL;DR
This paper proposes a multi-scale structural similarity (MS-SSIM) image quality method that combines contrast and structure comparisons across scales and luminance comparison at the coarsest scale. On the LIVE JPEG/JPEG2000 database, MS-SSIM outperformed PSNR, the Sarnoff model, and single-scale SSIM variants on all reported evaluation criteria.
Key findings
- MS-SSIM achieved the best reported performance: CC 0.969, ROCC 0.966, MAE 3.86, RMS 4.91, and OR 1.16%, compared with the best single-scale SSIM at M=2 (CC 0.963, ROCC 0.959, MAE 4.21, RMS 5.38, OR 2.62%) and PSNR (CC 0.905, ROCC 0.901, MAE 6.53, RMS 8.45, OR 15.7%).
- Single-scale SSIM performance varied with scale; the best single-scale result was at M=2, and single-scale SSIM tended to give higher scores as scale increased.
- The calibrated cross-scale exponents were β1=γ1=0.0448, β2=γ2=0.2856, β3=γ3=0.3001, β4=γ4=0.2363, and α5=β5=γ5=0.1333.
- The authors conclude that multi-scale SSIM provides a meaningful balance between scales and outperforms the best single-scale SSIM and state-of-the-art image quality metrics.
Methods
- The MS-SSIM system iteratively applies a low-pass filter and downsamples by 2; at each scale it computes contrast and structure comparisons, computes luminance comparison only at Scale M, and combines them using exponents normalized so that ∑γj=1.
- Cross-scale parameters were calibrated by image synthesis: 5 scales and 12 distortion levels (range 2^3 to 2^14) were used with 10 original 64×64 images, producing 600 distorted images; 8 subjects selected images of equal perceived quality across scales at a viewing distance of 32 pixels per degree of visual angle.
- Evaluation used the LIVE database with 344 JPEG and JPEG2000 compressed images (bit rate 0.028 to 3.150 bits/pixel), MOS from 13–25 subjective scores, and compared PSNR, Sarnoff JNDmetrix 8.0, single-scale SSIM for M=1–5, and MS-SSIM using CC, MAE, RMS, OR, and ROCC after logistic mapping.
Limitations
- Stated: the image-synthesis calibration approach is “still rather crude,” and the authors are working on a more systematic approach.
- Stated: CSF cannot be directly used to derive the parameters because it is typically measured at visibility threshold with simplified stimuli, whereas the goal is comparing complex structured images at visible distortion levels.
- Evident from the text: calibration used only 10 original 64×64 grayscale images and 8 subjects, including one author, and evaluation was limited to the LIVE JPEG/JPEG2000 database.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 Valid · 1 Not valid · 14 Not checked · 18 Own results and interpretations
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It can also be observed that the single-scale model tends to supply higher scores with the increase of scales.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Finally, for every one of the objective evaluation criteria, multi-scale SSIM model outperforms all the other models, including the best single-scale SSIM model, suggesting a meaningful balance between scales.”
- Also stated in: § 5. DISCUSSIONS · p. 4 · hedged
“Experiments show that with an appropriate parameter settings, the multi-scale method outperforms the best single-scale SSIM model as well as state-of-the-art image quality metrics.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 5. DISCUSSIONS · p. 4 · hedged
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In general, the subjects agreed with each other on each image more than they agreed with themselves across different images.”
plainstates an associationn = 8- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The resulting parameters we obtained are β 1 = γ 1 = 0.0448, β 2 = γ 2 = 0.2856, β 3 = γ 3 = 0.3001, β 4 = γ 4 = 0.2363, and α 5 = β 5 = γ 5 = 0.1333, respectively.”
plainn = 8- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“However, the SSIM index algorithm introduced in [5] is a single-scale approach.”
What the sources say
- Not matchedcites [5] [5] Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, 'Image quality assessment: From error measurement to structural similarity,' IEEE Trans. Image Processing , vol. 13, Jan. 2004. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
10 more claims
Create a free account to see all 33 claims and every source verdict.
- It may state two separate claims as one. 8
- Probably not a substantial claim. 13
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Further, as research in quality assessment has demonstrated, incorporating multiscale information when assessing quality produces QA algorithms that perform better in terms of correlation with human perception [13], [29].”
From No-Reference Image Quality Assessment in the Spatial Domain (2012) · cites this paper as [13]
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
Self-citationA universal image quality index
Wang, Z., & Bovik, A. C. (2002) · IEEE Signal Processing Letters · doi:10.1109/97.995823 · Cited by 5,757
Self-citationImage quality measures and their performance
Eskicioglu, A. M., & Fisher, P. S. (1995) · IEEE Transactions on Communications · doi:10.1109/26.477498 · Cited by 2,117
A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients
Portilla, J., & Simoncelli, E. P. (2000) · International Journal of Computer Vision · doi:10.1023/a:1026553619983 · Cited by 1,806
Self-citation(1995) · Medical Entomology and Zoology · Cited by 1,212
Pyramid-based texture analysis/synthesis
Heeger, D. J., & Bergen, J. R. (1995) · Proceedings of the 22nd annual conference on Computer graphics and interactive techniques - SIGGRAPH '95 · doi:10.1145/218380.218446 · Cited by 1,095
Video quality assessment based on structural distortion measurement
Wang, Z., Lu, L., & Bovik, A. C. (2004) · Signal Processing: Image Communication · doi:10.1016/s0923-5965(03)00076-6 · Cited by 1,024
Self-citationImage Quality Assessment: From Error Measurement to Structural Similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · Cited by 881
Self-citationTeo, P. C., & Heeger, D. J. (2002) · Proceedings of 1st International Conference on Image Processing · doi:10.1109/icip.1994.413502 · Cited by 471
Objective video quality assessment
(2003) · Handbook of Video Databases · doi:10.1201/9780203489864-45 · Cited by 359
Research works printed but not linked: 2
- 0, JNDmetrix Technology, Sarnoff Corporation
- 2000, Final report from the video quality experts group on the validation of objective models of video quality assessment, VQEG
Cited by
Items 5,001–5,100 of 6,047
Optimization of HVS-based objective image quality assessment with eye tracking
Fliegel, K. (2008) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.794801
A novel image fusion rule based on Structure Similarity indices
Su, S. C., & Wang, F. (2013) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2013.6745289
“SSIM is raised in [9] for the first time, which is a parameter used to describe the similarity between two images.”
MethodStatistical modeling of multi-camera images
Soundararajan, R., Bovik, A. C., & Vishwanath, S. (2009) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/acssc.2009.5469827
Self-citationAdvances in Image and Video Quality Assessment
(2012) · Springer eBooks · doi:10.1007/springerreference_72849
On the duality of rate allocation and quality indices
Richter, T. (2010) · Picture Coding Symposium · doi:10.1109/pcs.2010.5702484
Local masking in natural images measured via a new tree-structured forced-choice technique
Vilankar, K. P., & Chandler, D. M. (2011) · doi:10.1109/ivmspw.2011.5970348
Cabezas, I., & Trujillo, M. (2013) · Univalle Digital Repository (University of Valle)
Still image coding using a wavelet-like transform
Maalouf, A., Larabi, M., & Fernández-Maloigne, C. (2009) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2009.5413676
Machine-readable region identification from partially blurred document images
Wang, Q., Wang, Y., Wang, C., et al. (2015) · Proceedings of the International Conference on Document Analysis and Recognition · doi:10.1109/icdar.2015.7333758
High efficiency prediction methods for current and next generation video coding
Blasi, S. (2014) · Queen Mary Research Online (Queen Mary University of London)
A Novel Approach to Access the Quality of Tone Mapped Images
DEGALA, K., & RAJU.Y, D. S. (2014) · International Journal of Innovative Research in Science Engineering and Technology · doi:10.15680/ijirset.2014.0310051
Steering Kernel Regression via Laplacian for Image Denoising in Spatial Domain
Salami, R. (2014) · Eastern Mediterranean University Institutional Repository (Eastern Mediterranean University)
Iasbech, P. A. B., Freitas, C., Jorge, B. R., et al. (2014) · Revista de Radiodifusão · doi:10.18580/radiodifusao.2014.8.121
Quality metrics can help the expert during neurological clinical trials
Mahé, L., Autrusseau, F., Desal, H., et al. (2016) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2217776
Learning based signal quality assessment for multimedia communications
Narwaria, M. (2012) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/50753
“We also include the results for PSNR, MSSIM(2) [153], VSNR [45], VIF [44], PSNR-HVS-M [154] and DPS [146] all of which are FR schemes.”
MethodRede SFN Híbrida – Dificuldades de Implantação
Kusunoki, M., Pellegrini, L. V., & Rehme, J. F. (2014) · Revista de Radiodifusão · doi:10.18580/radiodifusao.2014.8.119
3D geometry-dependent texture map compression with a hybrid ROI coding
Yang, B. L., Jing, J., Wang, X., et al. (2013) · Science China Information Sciences · doi:10.1007/s11432-013-4897-3
High-performance power-efficient solutions for embedded vision computing
Tabkhivayghan, H. (2014) · doi:10.17760/d20018704
da Silva, W. B., & Pohl, A. D. A. P. (2013) · Revista de Radiodifusão · doi:10.18580/radiodifusao.2013.7.107
QP Selection Optimization for Intra-Frame Encoding Based on Constant Perceptual Quality
Wang, C., Mou, X., & Lei Zhang, A. (2016) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2015edp7183
“So, we use Multiscale SSIM (MS-SSIM) index [33] to measure the perceptual quality, which has been proved to have better correlation with human assessment.”
MethodCross-layer performance analysis and adaptation for real-time wireless video streaming
Loiacono, M. (2011) · Rutgers University Community Repository (Rutgers University) · doi:10.7282/t3zs2w41
“This motivated the development of the Multi-Scale SSIM (MS-SSIM) metric [67], which was shown to offer an improvement over SSIM.”
MethodVideo quality assessment based on a modified mean squared error
Loh, W.-T., Voo, K. H. B., & Bong, D. B. L. (2015) · IEEE International Conference on Signal and Image Processing Applications (ICSIPA) · doi:10.1109/icsipa.2015.7412242 · Cited by 1
“The most commonly used IQA is MSE, peak signal to noise Ratio (PSNR), structural similarity index (SSIM) [2], and multi-scale SSIM (MSSIM) [9].”
MethodAnálise de desempenho do sistema DVB-T2 para transmissão de 4K (UHD) usando 6 MHz de banda
Esperante, P. G., Akamine, C., Bedicks, G., et al. (2014) · Revista de Radiodifusão · doi:10.18580/radiodifusao.2014.8.115
Data rate and dynamic range compression of medical images: Which one goes first?
Athar, S., Yeganeh, H., & Wang, Z. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351645
“In [6], objective IQA metrics including PSNR, SSIM [7], MS-SSIM [8] and IW-SSIM [9] are employed to evaluate a final LDR image after windowing the HDR reference image to an intermediate LDR reference.”
MethodSelf-citationA Feature-level Image Fusion Performance Evaluating Measure based on Contourlet Transform
Guo, L., Du, Q., Sun, Q., et al. (2013) · Journal of Convergence Information Technology · doi:10.4156/jcit.vol8.issue6.129
“Begin from 2002, Zhou Wang put forward and perfected the structure model used to evaluate image quality, which had made great influence in the industry [10-12].”
MethodKim, D.-O., & Park, R. (2015) · Advances in Vision Computing An International Journal · doi:10.5121/avc.2015.2101
“The proposed CSF without weights gives the good performance next to the MSSSIM for all data.”
MethodInfluentialPerceptual video quality assessment for adaptive streaming encoding
Monteiro, E. C., Scholz, R. E. P., Ferraz, C. A. G., et al. (2015) · Visual Communications and Image Processing · doi:10.1109/vcip.2015.7457816
Advanced methods for controlling dual modulation display systems
Atkins, R. (2012) · cIRcle (University of British Columbia) · doi:10.14288/1.0072657
An Improved Image Quality Assessment in Gradient Domain
Ren, Y., Lu, W. B., He, L., & Xu, T. (2015) · Communications in computer and information science · doi:10.1007/978-3-662-48570-5_29
Une nouvelle métrique avec référence complète d'évaluation de la qualité d'images couleur
Ouni, S., & Zagrouba, E. (2012)
Saliency-aware Image Quality Assessment
Liu, Z., Huang, Y., Niu, Y., et al. (2016) · doi:10.2991/wartia-16.2016.280
Xu, L., Lin, W., & Kuo, C. ‐. J. (2015) · Springer briefs in electrical and computer engineering · doi:10.1007/978-981-287-468-9_4
Study of Noise Removal Techniques for Digital Images
Patel, P., Jena, B., Sahoo, B., et al. (2016) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-4666-9685-3.ch003
Deep Data Anaylizing Method Based on Scale Space Theory
Hu, Y., Chen, G., & Gao, K. (2016) · Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering · doi:10.18293/seke2016-097
BRIQA: Framework for the Blind and Referenced Visual Image Quality Assessment
Escobar, J. J. M., Matamoros, O. M., Padilla, R. T., et al. (2016) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2016.070842
“Thus, the correlation between the opinion of observers and the results of MSSIM is 0.0143 less than the ones of RIQA.”
MethodInfluentialFACE OBFUSCATION BASED REVERSIBLE WATERMARKING FOR TAMPER PROOF IRADICATION
., S. A. (2015) · International Journal of Research in Engineering and Technology · doi:10.15623/ijret.2015.0417021
Lu, Z., Zhou, S., Wen, X., Shao, H., & Fu, B. (2016) · Wireless Personal Communications · doi:10.1007/s11277-016-3737-3
“Several VQA methods are proposed based on SSIM, such as M-SSIM, CW-SSIM [5, 6].”
MethodGeneral Adaptive Monte Carlo Bayesian Image Denoising
Zhang, W. (2010) · UWSpace (University of Waterloo)
Designing a face detection CAPTCHA
Day, A. C. (2010) · doi:10.33915/etd.2953
Image Information Distance Analysis and Applications
Nikvand, N. (2014) · UWSpace (University of Waterloo)
Resolution enhancement of tri-stereo remote sensing images by super resolution methods
Tuna, Ç., Akoguz, A., Ünal, G., & Sertel, E. (2016) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2241176
“t extracting structural information from the scene, and therefore a measure of structural similarity can provide a good approximation to the perceived image quality.(16) The proposed SR methods are also applied to the real RS data.”
MethodAn Anatomy of SVC for Full HD Video Streaming
Zakerinasab, M. R., & Wang, M. (2014) · doi:10.1109/mascots.2014.50
“To quantify the objective quality, we calculate the Y-PSNR (the PSNR value of the luma component of the video sequence), SSIM (structural similarity index) [28], MS-SSIM (multi-scale structural similarity index) [29] and the pixel domain version of VIF (visual information fidelity) [30] for each encoded video sequence.”
MethodRevisiting the Regression between Raw Outputs of Image Quality Metrics and Ground Truth Measurements
Jung, C., Joo, S., Nam, D.-W., et al. (2016) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.2015edp7099
“For example, for LIVE database, the MS-SSIM [6] with pretrained machine-learning-based mapping gives correlation coe ffi cient of 0.9450 when the training is done only with TID2008 database, on the other hand, the naive MS-SSIM [6] gives correlation coe ffi cient of 0.9280.”
BackgroundMethodInfluentialEvert, J. (2015) · SHAREOK (University of Oklahoma; Oklahoma State University; Central Oklahoma University)
Screen content image evaluation and processing
Yang, H. (2015) · doi:10.32657/10356/65397
Objective Quality Assessment and Optimization for High Dynamic Range Image Tone Mapping
Ma, K. (2014) · UWSpace (University of Waterloo)
Image Quality Assessment Based on Contour and Region
Huang, C., Jiang, M. J. M., & Jiang, T. (2016) · Journal of Computational Mathematics · doi:10.4208/jcm.1611-m2016-0534
“In the following experiments, our model is compared with multiple state-of-the-art models such as MS-SSIM [6], IFC [7], VIF [8], VSNR [4], MAD [36], IW-SSIM [9], RFSIM [37], FSIMc [10], VSI [11].”
MethodVisual signal coding and quality evaluation
Liu, A. (2011) · doi:10.32657/10356/47587
Perceptual Video Quality Assessment and Enhancement
Zeng, K. (2013) · UWSpace (University of Waterloo)
A Biologically-Inspired Approach to Making HDR Video Quality Assessment Easier
McCarthy, S. T. (2017) · SMPTE Motion Imaging Journal · doi:10.5594/jmi.2017.2673718
Liu, H., Li, K., Wang, B., et al. (2017) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.11.015003
Multi-focus Image Fusion Algorithm Based on Multilevel Morphological Component Analysis
Wang, L., & Li, X. (2017) · doi:10.2991/ifmca-16.2017.40
“Five different objective measures including Mutual Information (MI) [7], Peak Signal to Noise Ratio (PSNR) [8], Structural Similarity (SSIM)[9], and Piella's metrics (Q, QW) [10] are used to evaluate the performance of the fusion algorithms.”
MethodPerceptual Assessment: Final tests and Analysis.Preprint
Barkowsky, M., Wang, J., Gautier, J., et al. (2013) · HAL (Le Centre pour la Communication Scientifique Directe)
GPGPU based Implementation of BLIINDS-II NR-IQA
Yadav, A. (2016)
Investigating the Adaptive Loop Filter in Next Generation Video Coding
Gomes-Arevalillo, A. D. L. R. (2017) · KTH Publication Database DiVA (KTH Royal Institute of Technology)
Learning data-driven image similarity measure
Kobayashi, T. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7900206
Photogrammetric point cloud compression for tactical networks
Madison, A. C., Massaro, R. D., Wayant, C. D., et al. (2017) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2266552
“The SSIM is a perception-based model that considers image degradation between to images, x and y, as perceived change in structural information, s (x,y), while also incorporating important perceptual phenomena, including both luminance, l (x,y), and contrast, c (x,y) masking factors.(17) The SSIM , which can be writte…”
BackgroundSubjective and Objective Quality-of-Experience of Adaptive Video Streaming
Duanmu, Z. (2017) · UWSpace (University of Waterloo)
A Simple Metric of IQA with Contourlet transformation
Liang, S., & Wang, G. (2017) · International Conference on Frontiers of Manufacturing Science and Measuring Technology (FMSMT) · doi:10.2991/fmsmt-17.2017.315
Single image super resolution based on content-aware constraint and intensity-order constraint
Shibata, T., & Sato, A. (2017) · doi:10.23919/mva.2017.7986824
Subjective and objective quality assessment for color changed images
Wang, A., Zhai, G., Chen, Y., Che, Z., & Yang, X. (2017) · IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB) · doi:10.1109/bmsb.2017.7986169
Escobar, J. J. M., Martínez‐González, C. L., Matamoros, O. M., et al. (2017) · Studies in computational intelligence · doi:10.1007/978-3-319-63754-9_29
Adaptive $$L_p$$ $$(0<p<1)$$ Regularization: Oracle Property and Applications
Shi, Y., He, X., Wu, H., et al. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-70087-8_2
Locally adaptive edge preserving filter for radar image denoising
Rubel, A., Лукин, В. В., & Shark, L. (2017) · IEEE Microwaves, Radar and Remote Sensing Symposium (MRRS) · doi:10.1109/mrrs.2017.8075042
A Contourlet coefficients based image quality metric
Liang, S., Wang, G., & Zhou, Z. (2017) · International Conference on Wavelet Analysis and Pattern Recognition · doi:10.1109/icwapr.2017.8076691
Capturing Localized Image Artifacts through a CNN-based Hyper-image RepresentationPreprint
Chandakkar, P. S., & Li, B. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.04945
“Few representative approaches that try to solve this problem are SSIM (Wang et al. 2004), MSSIM (Wang, Simoncelli, and Bovik 2003), FSIM (Zhang et al. 2011), VSI (Zhang, Shen, and Li 2014) etc.”
BackgroundMethodInfluentialNo Reference Stereoscopic Video Quality Assessment Using Joint Motion and Depth StatisticsPreprint
Appina, B., Akshith, J., Srinivas, B. S., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.05480 · Cited by 1
“We used the NIQE scores as spatial quality score in the proposed algorithm. Also, we compared our metric’s performance with different state-of-art 2D IQA/VQA and 3D IQA/VQA models. SSIM [64], MS-SSIM [65] are FR 2D IQA metrics and SBIQE [58], NIQE [60] and BRISQUE [59] are 2D NR IQA metrics. These IQA metrics were app…”
MethodInfluentialImage Quality Assessment of Enriched Tonal Levels Images
Zhao, J., Wen, W., & Khatibi, S. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-71598-8_13
Quality Assessment from Grayscale to Color Images
Hassan, A. M., & Bashraheel, M. S. (2017) · World Journal of Computer Application and Technology · doi:10.13189/wjcat.2017.050402
Image quality evaluation based on saliency and feature similarity
Pan, W., Sun, X., Wang, X., Wang, L., Xu, T., & Yang, B. (2017) · IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) · doi:10.1109/itnec.2017.8285100
Coupled convolution method for image processing
Fan, W., Liang, J., & Li, P. (2017) · IEEE International Conference on Unmanned Systems (ICUS) · doi:10.1109/icus.2017.8278399
“In order to verify the performance of the proposed EC algorithm, MS_SSIM [23] and PSNR are used to measure the perceptual quality of the image that is concealed from the proposed algorithm.”
MethodSurface Decimation by Scene Contents
Castelló, P. (2017) · International Journal of Computer Applications · doi:10.5120/ijca2017913400
Dihedral angle prediction using generative adversarial networksPreprint
Kim, H. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.10996
“MS-SSIM is a variant of single scale structural similarity [59].”
BackgroundSari, I., Juarna, A., Harmanto, S., et al. (2018) · International Journal of Electrical and Computer Engineering (IJECE) · doi:10.11591/ijece.v8i5.pp2847-2856
“MultiScale Structural Similarity Index (MS-SSIM): This is the metric defined in [11], that uses structural distortion as an estimate of the perceived visual distortion.”
MethodMotion-aware video quality assessment
Arvanitidou, M. G., & Sikora, T. (2017) · 2018 52nd Asilomar Conference on Signals, Systems, and Computers · doi:10.1109/acssc.2017.8335727
“The proposed method for the case of MSA-weighted MS-SSIM using the gmi (referred as MS-SSIM-MSA-GMI) outperforms the stateof-the-art motion models, which confirms the validity and the encourages further perspectives of the proposed approach.”
MethodFast magnetic resonance imaging based on high degree total variation
Wang, S., Lu, L., Zheng, J., et al. (2018) · AIP conference proceedings · doi:10.1063/1.5033647
Evolving Encoded Marking for Glove-Based Pose and Posture Recognition
Gyllinsky, J. V. (2018) · doi:10.23860/thesis-gyllinsky-joshua-2018
“Textures Special textures generated by machine learning techniques have also been used to fool other machine learning computer vision systems [3].”
MethodMulti-view near-InfrarediImage mosaicking for face detection in smart cities
M., S. K. K., Panetta, K. A., & Agaian, S. С. (2018) · Mobile Multimedia/Image Processing, Security, and Applications · doi:10.1117/12.2305011
An Image Representation for the 3D Face Synthesis
Luo, G., Zeng, W., Xie, W., Lei, H., & Xian, C. (2018) · Computer Animation (CA) · doi:10.1145/3205326.3205351
“We compute the structure similarity [18] between each pair of different facial expression, and the similarity matrix is shown in the range of percentage in [0; 100].”
MethodSynthesized view comparison method for no-reference 3D image quality assessment
Gu, X., Luo, F., Lin, C., et al. (2018) · International Conference on Graphic and Image Processing (ICGIP) · doi:10.1117/12.2302916
“We also calculate SSIM, MS-SSIM (Multi Scale SSIM) [18] and VIFP (Visual Information Fidelity Criterion in Pixel Domain) [19] between the final synthesized middle view and the middle view taken by a real camera, and use these popular full-reference image quality assessment metrics' performances as benchmarks for SVC.…”
MethodStaring at stars makes you see spots: Verifying images of red supergiant stars
Norris, R., & Baron, F. (2018) · doi:10.1117/12.2313504
Application of wavelets to improvement of defects visibility in active thermography
Kurpiński, M., & Fidali, M. (2018) · International Conference on Quantitative InfraRed Thermography (QIRT) · doi:10.21611/qirt.2018.p26
“Equation (2) shows the way of calculation of this measure [6]: SSIM(x, y) = (2μxμy+C1)(2σxy+C2) (μx2+μy2+C1)(σx2+σy2+C2) (2)”
MethodUsing texture measures for visual quality assessment
Freitas, P. G. (2017) · Americanae (AECID Library) · doi:10.13140/rg.2.2.36599.34728
Video Quality Assessment Algorithm Based on Persistence-of-Vision Effect
Liu, P., Liu, F., & Gong, D. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-00009-7_34
Multivariate Statistics for Blind Image Quality Applications
Gupta, P., Bampis, C. G., & Bovik, A. C. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451552
Self-citationVideo quality analysis framework for spatial and temporal artifacts
Wang, Y., & Adsumilli, B. (2018) · doi:10.1117/12.2322328
Scene-Aware Soccer Video QoE Assessment - A Compressed-Domain Approach
Li, F., Mei, Y., Liu, Z., et al. (2018) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2018.8486555
“Full reference metrics, such as PSNR, SSIM [1], and MSSSIM [2] are widely used as QoE metrics, and rely on full access to the original video.”
MethodSpatiotemporal Masking for Objective Video Quality Assessment
He, R., Lu, W. B., Zhang, Y., Gao, X., & He, L. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-03398-9_27
Mobile Sensor Network for Suspended Particulate Matter Measurements using Kriging Interpolation
Makowski, Ł. (2018) · doi:10.1109/cpee.2018.8506765
“Details of SSIM are thoroughly discussed in [13].”
BackgroundShao, C., & Nirjon, S. (2018) · International Conference on Distributed Computing in Sensor Systems (DCOSS) · doi:10.1109/dcoss.2018.00031
“The formula for computing the MS-SSIM score is given in Eq.”
MethodInfluentialToward an objective benchmark for video completion
Bokov, A., Vatolin, D. S., Ерофеев, М., et al. (2018) · Signal Image and Video Processing · doi:10.1007/s11760-018-1387-5
“We keep the multiscale scheme, as it allows us to separately capture distortions on different scales, to which the human visual system typically has different sensitivity [29].”
BackgroundMethodEffect of Illumination and Blur Change on Markerless Image Registration Methods
Gupta, N., & Rohil, M. K. (2018) · International Conference for Convergence in Technology (I2CT) · doi:10.1109/i2ct.2018.8529385
“2) Multi-Scale Structure SIMilarity Index (MS-SSIM): MSSSIM explores SSIM at multiple image scales to attain a consistent subjective evaluation of the change of measure in the distorted image from the referenced image [22].”
Incremental Scene SynthesisPreprint
Planche, B., Rong, X., Wu, Z., Karanam, S., Kosch, H., Tian, Y., Ernst, J., & Hutter, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.12297 · Cited by 5
“truth observations. The common L1 distance is computed as the per-pixel absolute difference between the predicted and expected values, averaged over each image. The structural similarity (SSIM) index [50,51], prevalent in the assessment of perceptual quality [52 ,53 54], is computed over Nwindows extracted from the pr…”
MethodSMIM: Superpixel Mutual Information Measurement for Image Quality Assessment
Wang, J., Lü, T., & Zhang, Y. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-05054-2_34
Intelligence Compatibility Test of Web Services-based Power Business
Chen, Z., Peng, T., Gong, S., et al. (2018) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac.2018.8577816
Optimal Design of Laplacian Pyramid for the Structural Similarity Index
Wan, L., Sheng, Y., Chai, L., et al. (2018) · Chinese Automation Congress · doi:10.1109/cac.2018.8623292
Metadata
- Authors
- Wang, Z., Simoncelli, E. P., & Bovik, A. C.
- Affiliations
- Courant Institute of Mathematical Sciences (US)
- The University of Texas at Austin (US)
- Venue
- The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003
- Publisher
- IEEE
- Published
- 2004-07-08
- Pages
- 1398-1402
- ISSN
- 1058-6393 (ISSN-L)
- OpenAlex
- W1580389772
- Cited by
- 6,253
- References
- 15
- Citations by year
- 2026: 344 · 2025: 675 · 2024: 729 · 2023: 668 · 2022: 662 · 2021: 641 · 2020: 563 · 2019: 438 · 2018: 305 · 2017: 267 · 2016: 206 · 2015: 173 · 2014: 166 · 2013: 112 · 2012: 89
- FWCI
- 3.98
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Asilomar Conference on Signals, Systems and Computers (ACSSC) (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
- structural similarity, image quality assessment, multiscale analysis, human visual system, perceptual image quality, image generation, parameter calibration, viewing conditions
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.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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.