Multiscale structural similarity for image quality assessment
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.
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. -
More than one paper fits this citation.
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 · cited 1×
“Traditional perceptual image quality assessment methods are based on a bottom-up approach which attempts to simulate the functionality of the relevant early human visual system (HVS) components.”
BackgroundA 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 · cited 2×
“These synthesis methods provide a powerful and efficient means of testing a model, and have the added benefit that the resulting images suggest improvements that might be made to the model [11].”
MethodSelf-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 919
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 4,201–4,300 of 6,047
Conditional Image Synthesis Using Stacked Auxiliary Classifier Generative Adversarial Networks
Yao, Z., Dong, H., Liu, F., et al. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-03405-4_29 · Cited by 2
Album cover generation from genre tags
Hepburn, A., McConville, R., & Santos‐Rodríguez, R. (2017) · Bristol Research (University of Bristol) · Cited by 2
Multiple Reconstruction Compression Framework based on PNG Image
Lu, Z., & Tang, J. (2019) · International Journal of Computational Science and Information Technology · doi:10.5121/ijcsity.2019.7401 · Cited by 2
Objective Image Quality Analysis of Convolutional Neural Network Light Field Coding
Medda, D., Song, W., & Perra, C. (2019) · European Workshop on Visual Information Processing · doi:10.1109/euvip47703.2019.8946230 · Cited by 2
“the signal sampling density, the distance between the image and the observer and the observer’s own visual system capabilities) [19].”
Variable Rate Video Compression using a Hybrid Recurrent Convolutional Learning Framework
Jadhav, A. (2020) · International Conference on Computer Communication and Informatics (ICCCI) · doi:10.1109/iccci48352.2020.9104085 · Cited by 2
“The frames from these three codecs are evaluated using the PSNR-HVS[12] and MS-SSIM [11] metrics.”
MethodA Novel Approach to Ultrasound Image Thresholding Using Phase Gradients
Sivanandan, R., & Jayakumari, J. (2020) · Lecture notes in electrical engineering · doi:10.1007/978-981-15-3992-3_7 · Cited by 2
Perceptual Evaluation of Pre-processing for Video Transcoding
Huang, S., Luo, Z., Xu, J., Zhou, W., & Chen, Z. (2021) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip53242.2021.9675438 · Cited by 3
“Considering the HVS, structure similarity between original and distorted images is measured in structural similarity index (SSIM) [11], with several variants, e.g. MS-SSIM [12] and FSIM [13].”
MethodPerception of video quality at a local spatio-temporal horizon: research proposal
Pastor, A., & Callet, P. L. (2022) · ACM Multimedia Systems Conference (MMSys) · doi:10.1145/3524273.3533931 · Cited by 2
“Some metrics for VQA are VMAF[21], SSIM[38], MS-SSIM[39], PSNR, FSIM[43], VSI[42] and MAD[15].”
Exploring Temporal Consistency in Image-Based Rendering for Immersive Video Transmission
Ravi, S. L., Henry, F., Morin, L., et al. (2022) · European Workshop on Visual Information Processing · doi:10.1109/euvip53989.2022.9922680 · Cited by 2
“The comparison of average quality of synthesized views using VMAF (higher means better), MS-SSIM (higher means better), and PSNR (higher means better) metrics with respect to various use cases. thetic or computer-generated sequences and the rest are real-world sequences.”
InfluentialPatch-Based Image Coding with End-To-End Learned Codec using Overlapping
Tarchouli, M., Pelurson, S., Guionnet, T., et al. (2022) · doi:10.5121/csit.2022.122305 · Cited by 2
Video Compression Using Convolutional Neural Networks of Video with Chroma Subsampling
Ghassab, V. K., Gonsalves, R., Mathur, S., et al. (2022) · doi:10.5594/m001957 · Cited by 2
Bokeh Rendering Based on Adaptive Depth Calibration Network
Liu, L., Zhou, L., & Dong, Y. (2023) · International Conference on Computer and Communication Systems (ICCCS) · doi:10.1109/icccs57501.2023.10151285 · Cited by 2
“Then, we combine the L1 loss function with the MS-SSIM loss function [17] for an additional 30 epochs.”
MethodTowards Accurate and Efficient Image Quality Assessment with Interest Points
Zhang, X., Wang, S., Ma, S., et al. (2015) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm.2015.58 · Cited by 2
Spatial upscaling of scalable coded video for mobile applications
Vranješ, D., Vranješ, M., & Rimac-Drlje, S. (2013) · International Symposium ELMAR · Cited by 2
Evaluation of full-reference objective video quality metrics on high efficiency video coding
Wallendael, G. V., Staelens, N., Leuven, S. V., et al. (2013) · Ghent University Academic Bibliography (Ghent University) · Cited by 2
A new image quality estimation approach for JPEG2000 compressed images
Chetouani, A., & Beghdadi, A. (2011) · IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) · doi:10.1109/isspit.2011.6151627 · Cited by 2
No-reference quality assessment of highly compressed video sequences
Dimitrievski, M., & Ivanovski, Z. A. (2013) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp.2013.6659299 · Cited by 2
“In he past several years, algorithms emerged that can mimic this human behavior with high degree of success [1-13].”
BackgroundInfluentialHou, X., Jiang, G., Ji, R., et al. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5651196 · Cited by 2
Spatiotemporal No-Reference Video Quality Assessment model on distortions based on encoding
Zerman, E., Akar, G., Konuk, B., & Nur, G. (2013) · Signal Processing and Communications Applications Conference · doi:10.1109/siu.2013.6531235 · Cited by 2
Image quality estimation for different spatial resolutions
Demirtaş, A. M., Reibman, A. R., & Jafarkhani, H. (2013) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2013.6738078 · Cited by 2
“The state-of-the-art QE methods are Structural Similarity Index (SSIM) [2], VIF [3], Visual Signal-to-Noise Ratio (VSNR) [4], PSNR, Multiscale-SSIM (MSSIM) [5], and Information Content Weighted SSIM (IWSSIM) [6].”
BackgroundMethodPerceptual image coding by standard-constraint codecs
Richter, T. (2009) · Picture Coding Symposium · doi:10.1109/pcs.2009.5167386 · Cited by 2
Image quality assessment based on independent component analysis
Luo, C., Wang, Y., Ding, Y. S., et al. (2014) · doi:10.1109/icosp.2014.7015139 · Cited by 2
“Comparison with other algorithms The performance of our algorithm is compared with other full reference algorithms [14] such as PQS [16], PSNR [17], IFC [18], SSIM [5] and MS-SSIM [6].”
BackgroundMethodEvaluation of a hyperspectral image database for demosaicking purposes
Larabi, M., & Susstrunk, S. E. (2010) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.876764 · Cited by 2
A multifunctional video quality assessment system
Gao, L., Xie, Y., Qi, J., & Li, Z. (2012) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp.2012.6469804 · Cited by 2
“SSIM (Structural SIMilarity) [1] is a recent popular method for IQA (Image Quality Assessment), which depends on the philosophy that natural images are highly structured and the HVS (Human Visual System) is sensitive to structural distortion.”
MethodViewing Distance-Based Perceived Error Control for Local Backlight Dimming
Yoo, D., & Han, K. (2015) · Journal of Display Technology · doi:10.1109/jdt.2014.2385795 · Cited by 2
An Image Fusion Assessment Metric Based on Multi-Scale Structure Similarity
Xiao, Z. S. (2012) · Applied Mechanics and Materials · doi:10.4028/www.scientific.net/amm.215-216.674 · Cited by 2
A content-adaptive sharpness enhancement algorithm using 2D FIR filters trained by pre-emphasis
Choi, I. H., Nam, Y., & Song, B. C. (2013) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2013.04.003 · Cited by 2
“Table 2 compares MSSSIM values for various algorithms.”
MethodInfluentialWavelet-based directional structural distortion model for image quality assessment
Cheng, G., Cheng, L., & Li, Y. (2010) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661810030041 · Cited by 2
Customising cost function for optimising image quality measures performances
Lahoulou, A., Viennet, E., Bouridane, A., & Haddadi, M. (2012) · International Journal of Electronics · doi:10.1080/00207217.2012.680792 · Cited by 3
Designing a biased specification-based subjective test of image quality
Reibman, A. R. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2086256 · Cited by 2
Single image super-resolution via sparse KPCA and regression
Yuan, T., Yang, W., Zhou, F., et al. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025427 · Cited by 2
“Our method surpasses all the compared methods in terms of PSNR, MS-SSIM and VIF.”
MethodInfluentialDifferential Energy Watermarking Based on Macro-block Prediction
Zeng, Q., & Feng, G. (2011) · International Conference on Computational Intelligence and Security (CIS) · doi:10.1109/cis.2011.209 · Cited by 2
Determination of the cause and amount of image degradation using a reduced reference approach
Bhattacharya, A., & Palit, S. (2013) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2013.6727051 · Cited by 2
“The multiresolution property of the Discrete Wavelet Transform (DWT) [14], [15] is employed for the construction of the feature.”
MethodA patch-based cross masking model for natural images with detail loss and additive defects
Liu, Y., & Allebach, J. P. (2015) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2083476 · Cited by 2
Tchebichef moment based image quality measure
lakshmi, D. K., Abudhahir, A., Begum, A. H. R., & Manimegalai, D. (2014) · International Conference on Electronics and Communication Systems (ICECS) · doi:10.1109/ecs.2014.6892724 · Cited by 2
Li, Q., Chang, T., & Jiao, X. (2012) · Proceedings of the ... IEEE International Conference on Virtual Environments, Human-Computer Interfaces and Measurement Systems./Proceedings of the ... IEEE International Conference on Virtual Environments, Human-Computer Interfaces and Measurement Systems · doi:10.1109/vecims.2012.6273193 · Cited by 2
A new scheme for no reference image quality assessment
Chetouani, A., Beghdadi, A., Bouzerdoum, A., & Deriche, M. A. (2012) · International Conference on Image Processing Theory, Tools and Applications (IPTA) · doi:10.1109/ipta.2012.6469534 · Cited by 6
An expert knowledge weighted model for evaluating medical image fusion
Zhang, X., Li, X., & Liu, Z. (2011) · International Conference on Computer Science and Service System · doi:10.1109/csss.2011.5974700 · Cited by 2
“Over the past decades, various objective image quality metrics emerge [1] [2] [3] [4] [5] [6].”
BackgroundClassification of image distortions using image quality metrics and linear discriminant analysis
Chetouani, A., Deriche, M. A., & Beghdadi, A. (2010) · European Signal Processing Conference (EUSIPCO) · Cited by 5
Improving edge-based feature extraction using feature fusion
Nercessian, S. C., Panetta, K. A., & Agaian, S. С. (2008) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/icsmc.2008.4811356 · Cited by 2
Regularized mre method for blind multichannel image deconvolution
Souidene, W., Beghdadi, A., Abed‐Meraim, K., et al. (2005) · 2018 52nd Asilomar Conference on Signals, Systems, and Computers · doi:10.1109/acssc.2004.1399564 · Cited by 2
Objective quality measures comparison of impaired 3D video sequences from the UC3D database
Dumić, E., Grgić, S., Cruz, L. A. D. S., & Assunção, P. (2014) · 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video · doi:10.1109/3dtv.2014.6874728 · Cited by 2
“The measures used were: • MS-SSIM (Multiscale Structural Similarity Index) [9], • PSNR (Peak Signal to Noise Ratio), • SSIM (Structural Similarity Index) [10], • VIF (Visual Information Fidelity) [11], • VSNR (Visual Signal-to-Noise Ratio) [12], • IW-SSIM (Information Weighted SSIM) [13], • IW-PSNR (Information Weight…”
Sequential error concealment via canonical correlation analysis
Fan, W., Liang, J., Ye, X., et al. (2015) · IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC) · doi:10.1109/icspcc.2015.7338931 · Cited by 2
Avaliação da Qualidade de Vídeo em Televisão Digital
Fonseca, R. N., & Ramírez, M. A. (2008) · Revista de Radiodifusão · doi:10.18580/radiodifusao.2008.3.32 · Cited by 2
Synthesis of phase and magnitude of images by Hermite projection method
Pavelyeva, E. A., & Krylov, A. S. (2015) · Pattern Recognition and Image Analysis · doi:10.1134/s1054661815020200 · Cited by 2
“The table shows the comparisons between synthesis methods by FT and AFTH using PSNR value and multi scale SSIM (MS SSIM) index [17] of some 256 × 256 grayscale images from SIPI Miscellaneous database [18] (first 15 images: 4.”
UHD image reconstruction by estimating interpolation error
Berger, K., Berger, K., & Callet, P. L. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351707 · Cited by 2
MR Image Compression Based on Selection of Mother Wavelet and Lifting Based Wavelet
Islam, S. M. R., Huang, X., & Le, K. (2014) · The International journal of Multimedia & Its Applications · doi:10.5121/ijma.2014.6206 · Cited by 2
“KEYWORDS CDF 9/7,MRI, Q(Kurtosis),Q(Skewness), SPIHT, UIQI .”
An Efficient Fusion Approach for Multispectral and Panchromatic Medical Imaging
He, C., Cao, G., & Lang, F. (2013) · Biomedical Engineering Research · doi:10.5963/ber0201004 · Cited by 2
Peculiarities of lossy compression of optical and medical images corrupted by noise
Krivenko, S., Лукин, В. В., & Kolganova, O. (2016) · IEEE International Conference on Electronics and Nanotechnology (ELNANO) · doi:10.1109/elnano.2016.7493060 · Cited by 2
Monitoring QoE on digital terrestrial TV: A comprehensive approach
Garella, J. P., Grampín, E., Sotelo, R., et al. (2016) · IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB) · doi:10.1109/bmsb.2016.7522008 · Cited by 2
“We have evaluated the classical “PSNR model”, the “PSNR-HVS model” [12], the “VQM General model” [13], the “VQM LowBW model” [14], the “SSIM model” [15], the “MS-SSIM model” [16], and the “VIFp model” (pixel domain version) [17].”
Calibration of Structural Similarity Index Metric to Detect Artefacts in Game Engines
Piórkowski, R., & Mantiuk, R. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46418-3_8 · Cited by 2
Predicting multiple target tracking performance for applications on video sequences
Tapiero, J. E., Medeiros, H. P., & Bishop, R. H. (2017) · Machine Vision and Applications · doi:10.1007/s00138-017-0840-8 · Cited by 2
“[72].”
Full-Reference Video Quality Estimation for Videos With Different Spatial Resolutions
Demirtaş, A. M., Reibman, A. R., & Jafarkhani, H. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2015.2473435 · Cited by 2
“PSNR, SSIM, and MSSIM are image QEs, and we apply them to video by averaging the quality of the frames.”
MethodInfluentialReduced Reference Quality Metric for Synthesized Virtual Views in 3DTV
Le, T. H., Long, V. T., Duong, D. T., et al. (2016) · ETRI Journal · doi:10.4218/etrij.16.2716.0041 · Cited by 2
“The validation methods are Synthesized Image Quality Evaluator (SIQE) [24] and other traditional full-reference methods, SSIM [25], multi-scale SSIM (MS-SSIM) [26], feature similarity (FSIM) [27], video quality metric (VQM) [28], and peak signal-to-noise ratio (PSNR).”
MethodAdaptive block truncation coding image compression technique using optimized dot diffusion
Liu, Y.-F., Guo, J.-M., & Cheng, Y. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7532736 · Cited by 2
Image Quality Assessment Using Edge Correlation
Ruikar, J. D., Sinha, A. K., & Chaudhury, S. (2017) · International Journal of Electronics and Telecommunications · doi:10.1515/eletel-2017-0014 · Cited by 2
Image quality measurement through structural similarity based on higher order moments
Kaur, S., Kour, H., & Sen, D. (2016) · IEEE India Conference · doi:10.1109/indicon.2016.7839044 · Cited by 2
New Tone-Mapped Image Quality Assessment Method Based on Color Space
Song, H., Jiang, G., Shao, H., et al. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-3966-9_42 · Cited by 2
A multi-stage temporal pooling mechanism for video quality assessment
Vivek Kumar., M., & Mahapatra, S. (2016) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/acssc.2016.7869705 · Cited by 2
“Tables II and III present the average correlation coefficient (CC) values obtained for the pooling mechanisms when the predicted video level quality scores of the pooling mechanisms corresponding to two full reference objective quality metrics, namely, peak-signal-to-noise ratio (PSNR) [13] and multi-scale structural…”
ResultBrunnstrom, K. E., Allison, R. S., Chandler, D. M., Colett, H. R., Corriveau, P., Daly, S. J., Goel, J., Knopf, J., Wilcox, L. M., Yaacob, Y., et al. (2017) · Electronic Imaging · doi:10.2352/issn.2470-1173.2017.14.hvei-131 · Cited by 3
“Such metrics are in high demand, given the increasing requirements for real-time image compression needed to deal with the bandwidth requirements of high-resolution image transmission [21, 34].”
BackgroundA Comparative Study of Objective Video Quality Assessment Metrics
Mello, C. A. B., Menor, D. P. A., Saraiva, M. M., et al. (2020) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.3217/jucs-023-05-0505 · Cited by 2
Near-surface lighting estimation and reconstruction
Zhang, Q., Tian, F.-P., Han, R., et al. (2017) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2017.8019481 · Cited by 2
“And 3 out of 6 are best on SSIM and MS-SSIM criteria, the other 3 gain the second highest score and are quite close to the best one, with at most 1.01% SSIM score and 0.48% MS-SSIM score lower than the best.”
BackgroundMethodInfluentialProof-of-concept: role of generic content characteristics in optimizing video encoders
Aldahdooh, A., Barkowsky, M., & Callet, P. L. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5180-1 · Cited by 2
“Methods like SSIM [48], MS-SSIM [50], PSNR-HVS [12], PSNR-HVS-M [34], VIFp [37], and VQM [30] can be tested and it is recommended as a future work.”
MethodReinhard's global operator based inverse tone mapping with one parameter
Kinoshita, Y., Shiota, S., & Kiya, H. (2017) · International Workshop on Signal Design and its Applications in Communications · doi:10.1109/iwsda.2017.8095734 · Cited by 2
“2 ∈ [0, 100] and PU encoding + MS-SSIM ∈ [0, 1], whose lager score indicates a higher similarity between two images.”
BackgroundShin, S., Kong, K., Lee, J., Song, W., Kwon, K. J., & Kim, S. G. (2017) · Journal of the Society for Information Display · doi:10.1002/jsid.612 · Cited by 2
“As metrics of objective evaluation, we used the tone-mapping quality index (TMQI), 26 which is widely used in tone mapping, and multiscale structural similarity (MS-SSIM), 27 which is widely used for image comparison.”
MethodAdaptive method for MRI enhancement using squared eigenfunctions of the Schrödinger operator
Chahid, A., Serrai, H., Achten, E., et al. (2017) · IEEE Biomedical Circuits and Systems Conference (BioCAS) · doi:10.1109/biocas.2017.8325107 · Cited by 2
“For the real data, the selection is driven by maximizing SSIM and SI .”
MethodInfluentialPursuit of Low-Rank Models of Time-Varying Matrices Robust to Sparse and Measurement Noise
Akhriev, A., Mareček, J., & Simonetto, A. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.5714 · Cited by 4
“First, we present MS-SSIM of [37], a well-known measure of similarity of the background of each frame to our rank-4 estimate thereof, which is also known as the multiscale structural similarity for image quality.”
MethodSteered Mixture-of-Experts Approximation of Spherical Image Data
Verhack, R., Madhu, N., Wallendael, G. V., et al. (2018) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco.2018.8553065 · Cited by 2
“The average loss over all images is 0.1 dB PSNR and 0.002 MS-SSIM.”
BackgroundInfluentialReliability of Local Ground Truth Data for Image Quality Metric Assessment
Piórkowski, R., & Mantiuk, R. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-03658-4_5 · Cited by 2
Restoration of Images Affected by Welding Fume
Vaz, E. S., Drews, P., & Steffens, C. R. (2018) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi.2018.00016 · Cited by 2
VMQ: an algorithm for measuring the Video Motion Quality
Alsrehin, N. O., & Klaib, A. F. (2019) · Bulletin of Electrical Engineering and Informatics · doi:10.11591/eei.v8i2.1418 · Cited by 2
“VMQ uses the MS-SSIM [9] for the comparison.”
MethodInfluentialZhang⋆, Y., Bai, X., Yan, J., et al. (2019) · Journal of Imaging Science and Technology · doi:10.2352/j.imagingsci.technol.2019.63.6.060504 · Cited by 2
“…used IQA methods include: PSNR (peak signal-to-noise ratio), WSNR (weighted signal-to-noise ratio), SSIM [19] (structural similarity), MS-SSIM [20] (multi-scale SSIM), CW-SSIM [21] (SSIM in complex wavelet domain), VIF [3], VIFp [3] (VIF in pixel domain), IFC [2], FSIM [22] (feature…”
Full-Reference Metric Adaptive Image Denoising
Hara, K., Inoue, K., & Urahama, K. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803231 · Cited by 2
An improved objective metric to predict image quality using deep neural networks
Akyazi, P., & Ebrahimi, T. (2019) · Electronic Imaging · doi:10.2352/issn.2470-1173.2019.12.hvei-214 · Cited by 2
Image fidelity estimation from received embedded bitstream
Baig, M. A., Moinuddin, A. A., Khan, E., et al. (2019) · Signal Image and Video Processing · doi:10.1007/s11760-019-01577-3 · Cited by 2
“Over the years, a large number of objective IQA algorithms have been proposed [2–9].”
BackgroundMethodImage Super-Resolution Improved by Edge Information
Galindo, E. S., & Pedrini, H. (2019) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2019.8914550 · Cited by 2
“In these methods, the values of similarity vary from 0 (the images are not similar) to 1 (the images are similar) [19], [20].”
Deep learning inversion of seismic data in tunnels
Liu, B., Yang, S., Xu, X., et al. (2020) · doi:10.1190/iwmg2019_13.1 · Cited by 3
Roth, T., Weier, M., Bauszat, P., et al. (2020) · Computers · doi:10.3390/computers9010017 · Cited by 2
Zheng, Z., Liu, Y., Liu, Y., Huang, B., & Yu, H. (2020) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2020.102848 · Cited by 2
Towards Semantically Scalable Image Coding using Semantic Map
Yan, N., Liu, D., Li, H., et al. (2020) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas45731.2020.9180529 · Cited by 2
Image Encryption Using Genetic Algorithm and Bit-Slice Rotation
Nandini, A. V., & Kumar, N. A. (2020) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt49239.2020.9225312 · Cited by 2
“Structural Similarity Index Measure (SSIM) is used to measure the similarity between two images [19].”
MethodThe effect of controlling the weight variable on the typeface attribute assessment
Žarko, J., & Nedeljković, U. (2020) · International Symposium on Graphic Engineering and Design (GRID) · doi:10.24867/grid-2020-p80 · Cited by 2
Structure Similarity for Image Quality Assessment from Isotropic to Anisotropic
Chang, Y., Zhang, X., & Zhu, D. (2021) · International Conference on Control Engineering and Artificial Intelligence (CCEAI) · doi:10.1145/3448218.3448226 · Cited by 2
QI-BRiCE: Quality Index for Bleeding Regions in Capsule Endoscopy Videos
Usman, M. A., Usman, M. R., Satrya, G. B., Khan, M. A., Politis, C., Philip, N. Y., & Shin, S. Y. (2021) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2021.014696 · Cited by 2
Laaroussi, S., Baataoui, A., Halli, A., et al. (2020) · IET Image Processing · doi:10.1049/iet-ipr.2020.0614 · Cited by 2
“This can also be seen with the results of the SSIM, MS-SSIM and BRISQUE values in Tables 1–3 where the proposed approach has the highest value for both measures even though the other methods gave good results.”
MethodInfluentialFproi-GAN with Fused Regional Features for the Synthesis of High-Quality Paired Medical Images
Dong, J., Liu, C., Man, P., et al. (2021) · Journal of Healthcare Engineering · doi:10.1155/2021/6678031 · Cited by 2
“In the tumor domain, the Fp roi -GAN values were 3.657, 0.085, and 0.042 higher than those of the cycleGAN method in the three evaluation metrics of PSNR, SSIM, and MS-SSIM, respectively, and 4.911, 0.095, and 0.052 higher than the DCGAN method, respectively.”
MethodInfluentialA Single Historical Painting Super-Resolution via a Reference-Based Zero-Shot Network
Shi, H., Xu, D., Zhang, H., & Yue, Y. (2021) · International Journal of Computational Intelligence Systems · doi:10.2991/ijcis.d.210503.002 · Cited by 2
“In terms of the measure of similarity, some works [62–64] showed that pixel-level similarity criteria, such as the PSNR, are better suited for identifying pixel-level image differences rather than the high-frequency texture details.”
ResultVisual perception of computer-generated stereoscopic pictures: Toward the impact of image resolution
Li, L., Chen, C., Hu, X., Liu, Y., & Liang, W. (2021) · Signal Processing Image Communication · doi:10.1016/j.image.2021.116301 · Cited by 3
An Attention Based Wavelet Convolutional Model for Visual Saliency Detection
Bhooshan, R. S., & Suresh, K. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413755 · Cited by 2
“…being a salient region, respectively, H and W is the height and width of G and S and represents the tuning parameter for positive and negative samples calculated as 0.568 from the ground truth samples of the training set as, SSIM [20] gives the measure of structural similarity be-tween two images.”
MethodInfluentialSubjective Quality Optimized Efficient Image Compression
Wang, X., Chen, T., & Ma, Z. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00216 · Cited by 2
“[6] Image compression methods mentioned above were mainly optimized for MSE or MS-SSIM [14], which failed to closely match the subjective quality of human perception.”
MethodInfluentialAdversarial and adaptive tone mapping operator: multi-scheme generation and multi-metric evaluation
Cao, X., Lai, K., Smith, M. R., et al. (2021) · Journal of Electronic Imaging · doi:10.1117/1.jei.30.4.043020 · Cited by 2
“In generating 1024 × 2048 resolution images, our proposed adTMO outperforms all other TMOs with regard to the metrics TMQI, SSIM, and MS-SSIM and outperforms most other TMOs with regard to FID and PPL.”
MethodInfluentialHybrid Learning of Non-Cartesian K-Space Trajectory and Mr Image Reconstruction Networks
Radhakrishna, C. G., Ramzi, Z., & Ciuciu, P. (2022) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi52829.2022.9761408 · Cited by 2
“a weighted sum of `1, `2 and multi-scale structural similarity index (S) [23]:”
BackgroundDetermining the Composition of a Mixed Material with Synthetic Data
Ly, C., Nizinski, C. A., Toydemir, A., et al. (2021) · Microscopy and Microanalysis · doi:10.1017/s1431927621012915 · Cited by 2
DENOISING SWEPT SOURCE OPTICAL COHERENCE TOMOGRAPHY VOLUMETRIC SCANS USING A DEEP LEARNING MODEL
Ledesma-Gil, G., Mao, Z., Liu, J. J., & Spaide, R. F. (2021) · Retina · doi:10.1097/iae.0000000000003348 · Cited by 2
Salient Object Detection Based on Multi-layer Cascade and Fine Boundary
Sun, D., Lv, X., Huang, S., Yao, L., & Ding, Z. (2021) · International Conference on Computational Intelligence and Security (CIS) · doi:10.1109/cis54983.2021.00069 · Cited by 3
Image Compression Based on Hybrid Domain Attention and Postprocessing Enhancement
Bao, Y., Tao, Y., & Qian, P. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/4926124 · Cited by 5
“,ere are two commonly used distortion metrics, namely, multiscale structural similarity (MS-SSIM) and mean square error (MSE) [31].”
MethodMaking Video Quality Assessment Models Sensitive to Frame Rate Distortions
Madhusudana, P. C., Birkbeck, N., Wang, Y., Adsumilli, B., & Bovik, A. C. (2022) · IEEE Signal Processing Letters · doi:10.1109/lsp.2022.3162159 · Cited by 3
“In our experiments we use four leading VQA models : SSIM [7], MS-SSIM [8], ST-RRED [11] and SpEED [12].”
MethodSelf-citationShi, R., Wang, W., Li, Z., He, L., Sheng, K., Ма, Л., Du, K., Jiang, T., & Huang, T. (2022) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2022.842760 · Cited by 3
“, 2019), and quality assessment research (Wang et al., 2003; Wang and Bovik, 2006; Vu et al., 2018).”
BackgroundUnderstanding Banding—Perceptual Modeling and Machine Learning Approaches for Banding Detection
Yeganeh, H., Zeng, K., & Wang, Z. (2022) · SMPTE Motion Imaging Journal · doi:10.5594/jmi.2022.3155759 · Cited by 2
Self-citationHierarchical Feature Aggregation Network for Deep Image Compression
Li, W., Du, Z., He, H., Tang, J., & Wu, G. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746628 · Cited by 3
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.