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 4,601–4,700 of 6,047
Objective method to provide ground truth for IQA research
Lu, Y., Xie, F., Jiang, Z., & Meng, R. (2013) · Electronics Letters · doi:10.1049/el.2013.1188 · Cited by 1
Performance evaluation of mail-scanning cameras
Rajashekar, U., Vu, T. T., Hooning, J. E., et al. (2010) · Journal of Electronic Imaging · doi:10.1117/1.3421975 · Cited by 1
Self-citationPerceiving distortions in visual signals
Bovik, A. C. (2011) · European Workshop on Visual Information Processing · doi:10.1109/euvip.2011.6045556 · Cited by 1
Self-citationEstimating an End-User's Received Video Signal at the Transmitter Using Cross-Layer Feedback
Loiacono, M. (2011) · International Conference on Communications · doi:10.1109/icc.2011.5962597 · Cited by 1
“The signals are compared using the Mean Squared Error (MSE) and the popular MS-SSIM metric [12] as shown in Table I.”
MethodNew image quality metric using derivative filters and compressive sensing
Kim, D.-O., Park, R., & Lee, J. W. (2010) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2010.5652810 · Cited by 1
“A multi-scale SSIM (MSSSIM) was proposed [4].”
MethodReconstruction of incomplete decoded videos for use in objective quality metrics
Sedano, I., Kihl, M., Brunnstrom, K. E., et al. (2012) · Lund University Publications (Lund University) · Cited by 1
Image quality assessment with visual sensitivity
Kuo, T.-Y., Tsai, C.-M., Chuang, C.-P., et al. (2015) · International Conference on Informatics, Electronics & Vision (ICIEV) · doi:10.1109/iciev.2015.7334032 · Cited by 1
Three-dimensional terrain model multiview quality assessment considering human visual system
Zhang, F., Li, X., Liu, H., Li, W., Hu, W., & Li, H.-C. (2015) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.9.097290 · Cited by 1
On SSIM-bit rate comparison of HEVC encoders
Zhao, T., Wang, Z., Kwong, S., & Chen, C. W. (2015) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.1109/apsipa.2015.7415514 · Cited by 2
Self-citationBlind image quality assessment of multi-degraded images
Kalatehjari, E., & Yaghmaee, F. (2014) · International Conference on Computer and Knowledge Engineering · doi:10.1109/iccke.2014.6993396 · Cited by 1
Image Quality Assessment Using the Motif Scan
Cui, Z. (2012) · Signal & Image Processing An International Journal · doi:10.5121/sipij.2012.3504 · Cited by 1
“Three categories are structural information based [2–14], human perception/visual attention based [15– 25], and information theoretical approaches [26, 27].”
BackgroundMethodPonomarenko, N. N., Лукин, В. В., Astola, J. T., et al. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-23234-8_45 · Cited by 1
Methodology for Increasing the Measurement Accuracy of Image Features
Majurski, M. P., Chalfoun, J., Lund, S. P., et al. (2016) · IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2016.176 · Cited by 1
Temporal video quality assessment method involving structural similarity index
Loh, W.-T., & Bong, D. B. L. (2016) · IEEE International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan) · doi:10.1109/icce-tw.2016.7520921 · Cited by 1
“Some existing popular IQA method are mean squared error (MSE) [1] [2], structural similarity (SSIM) index [3] and multi-scale structural similarity (MSSIM) [4].”
BackgroundInfluentialPerceptual Criteria on Image Compression
Escobar, M. D. C. M., & Jaime, J. A. (2011) · TDX (Tesis Doctorals en Xarxa) · Cited by 1
Recent improvements to Thor with emphasis on perceptual coding tools
Davies, T. I., Bjøntegaard, G., Fuldseth, A., et al. (2016) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2238836 · Cited by 2
Scotopic Visual Image Mining Based on NR-IQAF
Tian, F., Lv, X., Jiaji, C., & Xie, Z. (2011) · Communications in computer and information science · doi:10.1007/978-3-642-24091-1_38 · Cited by 1
FPGA implementation of PSO-based object tracking system using SSIM
El-Den, N. N., Abdelhalim, M. B., & Shehata, K. A. (2013) · doi:10.1109/icm.2013.6735003 · Cited by 1
Wang, Z., Wang, W., Li, Z., Wang, J., & Lin, W. (2012) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · Cited by 1
Self-citationBlind image restoration method by PCA-based subspace generation
Sumali, B., Hamada, N., & Mitsukura, Y. (2015) · International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) · doi:10.1109/ispacs.2015.7432766 · Cited by 1
“Typically, FR-IQA algorithms [11]-[13] calculate the distance between a test image with a pristine version of the image.”
BackgroundNo-reference image sharpness Algorithm based on gradient shape
Ni, J., Luo, G., Yu, T., & Li, N. (2016) · International Congress on Image and Signal Processing (CISP) · doi:10.1109/cisp-bmei.2016.7852816 · Cited by 1
“The typical research achievements such as MS-SSIM [4]、SSIM [3] and VSNR [5] .”
MethodHierarchical Gradient Similarity Based Video Quality Assessment Metric
Yang, J., Xiong, J., Gui, G., Song, R., Luo, W., & Long, X. (2017) · Algorithms · doi:10.3390/a10030072
Martínez-Rach, M., Piñol, P., López-Granado, O., et al. (2017) · DCC · doi:10.1109/dcc.2017.34 · Cited by 1
Image Noise Filter Based on DCT and Fast Clustering
Felipe, M. D. J. M., Riverón, E. M. F., Ramírez, P. M., et al. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-59226-8_15 · Cited by 1
A Feature-Based Quality Metric for Tone Mapped Images
Gao, X., Brooks, S., & Arnold, D. V. (2017) · ACM Transactions on Applied Perception · doi:10.1145/3129675 · Cited by 1
“Yeganeh and Wang [27] introduced the tone mapped image quality index (TMQI) by combining the measures of structural fidelity (modified multi-scale SSIM [26]) and statistical naturalness.”
MethodGraph-based interpolation for zooming in 3D scenes
Akyazi, P., & Frossard, P. (2017) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco.2017.8081310 · Cited by 1
“PSNR and MSSIM [20] values are presented in Tables I-IV.”
MethodInfluentialMultiscale Image Quality Estimation
Demirtaş, A. M., Reibman, A. R., & Jafarkhani, H. (2013) · eScholarship (California Digital Library) · Cited by 2
A Novel Image Fusion Algorithm Based on Structural Similarity
Zhou, Y., Su, Z., & Yang, X. (2017) · International Conference on Multimedia and Image Processing (ICMIP) · doi:10.1109/icmip.2017.63 · Cited by 1
Image Quality Assessment Based on Natural Image Statistics
Ding, Y. S. (2018) · Springer eBooks · doi:10.1007/978-3-662-56497-4_6 · Cited by 1
Evaluating grade of tone mapped high dynamic range images
A.M.Mane, T. D. D., & Tamboli, S. S. (2017) · doi:10.1109/cspc.2017.8305901 · Cited by 1
“SSIM technique [3] along with its multiscale derivations [4][5], is the first one.”
MethodPerformance assessment of three-dimensional video codecs in mobile terminals
Sánchez, A., Toril, M., Solera-Delgado, M., Luna-Ramírez, S., & Gómez, G. (2018) · Computer Communications · doi:10.1016/j.comcom.2018.04.016 · Cited by 1
“The reader is referred to [47] for more details about MS-SSIM.”
Comparison of machine learning-based feature pooling strategies for colour image fidelity assessment
Moan, S. L., & Bailey, D. G. (2017) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2017.8402454 · Cited by 1
Can image quality features predict visual change blindness?
Moan, S. L. (2017) · International Conference on Image and Vision Computing New Zealand (IVCNZ) · doi:10.1109/ivcnz.2017.8402492 · Cited by 1
Blind Image Quality Assessment Based on Natural Statistics of Double-Opponency
Sybingco, E., & Dadios, E. P. (2018) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2018.p0725 · Cited by 1
Quality Assessment of Thumbnail and Billboard Images on Mobile Devices
Sinno, Z., Moorthy, A. K., Cock, J. D., Li, Z., & Bovik, A. C. (2018) · Picture Coding Symposium · doi:10.1109/pcs.2018.8456285 · Cited by 2
“We computed Pearson’s Linear Correlation Coefficient (LCC) and Spearman’s rank correlation coefficient (SROCC) to assess the following IQA model performances on the new dataset: Peak-Signal to-Noise Ratio (PSNR), PSNR-HVS [12], Structural Similarity Index (SSIM) [3], Multi-Scale Structural Similarity Index (MS-SSIM) […”
MethodInfluentialSelf-citationLiu, Y., & Yang, J. (2018) · Optical Engineering · doi:10.1117/1.oe.57.10.103102 · Cited by 1
Towards a Referenceless Visual Quality Assessment Model Using Binarized Statistical Image Features
Freitas, P. G., Akamine, W. Y. L., & Farias, M. C. Q. (2018) · Brazilian Conference on Intelligent Systems · doi:10.1109/bracis.2018.00048 · Cited by 1
“This SSIM modification led to a performance improvement in comparison to the original SSIM.”
BackgroundInfluentialNo Reference Image Quality Assessment Based on Deep Learning with Distortion Type Prediction
TAKAGI, M., HIGURASHI, D., & Sakurai, A. (2018) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.30.6_823 · Cited by 2
“その他にも,VSNR [4] や 参照画像と劣化画像の相互情報量を用いる VIF [5]など人 間の視覚特性を利用した評価指標が多く提案されている [6].”
Optimizing the Performance of Halftoning-Based Block Truncation Coding
Xu, Z.-X., Chan, Y., & Lun, P. K. D. (2018) · Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) · doi:10.23919/apsipa.2018.8659744 · Cited by 1
Improvement of MRI images through heterogeneous interpolation techniques
Mújica‐Vargas, D., Mujica-Vargas, Y., Cruz, M. M., & Rendón-Castro, A. (2019) · International Conference on Electronics, Communications, and Computers · doi:10.1109/conielecomp.2019.8673230 · Cited by 2
Mojoo, J., Sabri, M., & Kurita, T. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8852127 · Cited by 1
A multi-stream dense network with different receptive fields to assess visual quality
Gonçalves, L., Zampolo, R. F., & Barros, F. J. B. (2019) · doi:10.5753/kdmile.2019.8790 · Cited by 1
“A short list of popular perceptual full reference IQMs, object of our study, follows: SSIM [Wang et al. 2004], MS-SSIM [Wang et al. 2003], FSIM [Lin Zhang et al. 2011], and HaarPSI [Reisenhofer et al. 2018].”
MethodAdaptive Block Matching Based Quantization for Lossy Image Compression
Ponomarenko, N. N., & Egiazarian, K. (2019) · European Workshop on Visual Information Processing · doi:10.1109/euvip47703.2019.8946146 · Cited by 1
QoE and Video Quality Evaluation for HTTP Based Adaptive Streaming
Arsenovic, M., & Rimac-Drlje, S. (2019) · Telecommunications Forum (TELFOR) · doi:10.1109/telfor48224.2019.8971378 · Cited by 1
Quality Assessment for Natural and Screen Content Images
Loh, W.-T., Joseph, A., & Bong, D. B. L. (2019) · IEEE International Conference on Signal and Image Processing Applications (ICSIPA) · doi:10.1109/icsipa45851.2019.8977791 · Cited by 1
The Endoscopic Images Visualization in Clinical Decision Support Systems
Obukhova, N. A., Motyko, A. A., & Pozdeev, A. A. (2020) · International Conference on Digital Signal Processing and its Applications (DSPA) · doi:10.1109/dspa48919.2020.9213285 · Cited by 1
“MSSIM [10] mean structural similarity index (SSIM [11]) with averaging over the local window.”
MethodModel Parameter Learning for Real-Time High-Resolution Image Enhancement
Song, Y., Zhu, Y., & Du, X. (2020) · IEEE Signal Processing Letters · doi:10.1109/lsp.2020.3029738 · Cited by 1
Yu, X., Liu, H., Han, X., Li, Z., Xiong, Z., & Cui, S. R. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3414001 · Cited by 1
A Novel Algorithm to Detect Brain Tumor using Staged-Type-II Fuzzy Classifier
Das, A., & Chatterjee, S. (2020) · IEEE Symposium Series on Computational Intelligence · doi:10.1109/ssci47803.2020.9308426 · Cited by 1
“The two parts are taken as two images and the structural similarity index (SSIM) [31] is determined for one image while taking the other as the reference image.”
BackgroundJoint Source Separation and Classification Using Variational Autoencoders
Hızlı, Ç., Karamatlı, E., Cemgil, A. T., et al. (2020) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu49456.2020.9302092 · Cited by 1
“Görüntü kayna˘gı ayırma kalitesi için tepe sinyal-gürültü oranı (PSNR) ve yapısal benzerlik indeksi ölçümü (SSIM) [13] kullanılmaktadır.”
Xu, P., Guo, M., Chen, L., Hu, W., Chen, Q., & Li, Y. (2021) · Complexity · doi:10.1155/2021/8834652 · Cited by 1
Mandhana, V., Agrawal, T., & Sardana, A. (2021) · ACM Symposium on Applied Computing · doi:10.1145/3412841.3441971 · Cited by 1
“To evaluate the image quality, we use metrics such as IS [15], FID [7], SSIM [21], MS-SSIM [19] and PSNR.”
MethodJoint Subtitle Extraction and Frame Inpainting for Videos with Burned-In Subtitles
Xu, H., He, Y., Li, X., Hu, X., Hao, C., & Jiang, B. (2021) · Information · doi:10.3390/info12060233 · Cited by 3
“In order to make an objective comparison between other existing methods and our method in terms of frame inpainting, the image quality metrics: Peak Signal-to-Noise Ratio (PSNR) [38], Structural SIMilarity (SSIM) [39], Normalized Root Mean Square Error (NRMSE), and Fréchet Inception Distance (FID) [40] were calculated…”
MethodAEE-Net: An Efficient End-to-End Dehazing Network in UAV Imaging System
Cai, T., Zhang, S., & Tan, B. (2021) · International Conference on Machine Learning and Computing (ICMLC) · doi:10.1145/3457682.3457739 · Cited by 1
“The MS_SSIM loss is given by where the β j values were obtained through psychophysical measurement [19].”
MethodEnhancement of Pixel-based Video Quality Models using Meta-data
Rao, R. R. R., Göring, S., & Raake, A. (2021) · Electronic Imaging · doi:10.2352/issn.2470-1173.2021.9.iqsp-264 · Cited by 1
Aziz, M. W., Nizami, I. F., & Majid, M. (2021) · doi:10.1109/icit52682.2021.9491779 · Cited by 2
RAVA: Region-Based Average Video Quality Assessment
Wu, X., Cheng, I., Zhou, Z., & Basu, A. (2021) · Sensors · doi:10.3390/s21165489 · Cited by 1
Implicit structural modeling of geological structures with deep learning
Bi, Z., & Wu, X. (2021) · Second International Meeting for Applied Geoscience & Energy · doi:10.1190/segam2021-3583427.1 · Cited by 2
Generative Difference Image for Blind Image Quality Assessment
Han, Y., Wang, Y., & Ma, Y. (2021) · International Conference on Computer Engineering and Artificial Intelligence (ICCEAI) · doi:10.1109/icceai52939.2021.00021 · Cited by 1
GSW: A High Performance IQA Index Based on Global and Saliency Window Similarity
Fan, Y., & Meng, Z. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2025/1/012061 · Cited by 2
“SSIM MSSSIM [13] IWSSIM [14] IFC VIF MAD [10] FSIM FSIMc GSM VSI GDRW GSW”
MethodA Study on Distortion Estimation Based on Image Gradients
Chin, S. C., Chow, C., Kanesan, J., & Chuah, J. H. (2022) · Sensors · doi:10.3390/s22020639 · Cited by 1
“The Multi-scale SSIM (MS-SSIM) extends the idea of the SSIM and changes the final consolidation score formula to obtain a more accurate grading [40].”
MethodLiu, F., Li, G., & Lin, L. (2021) · IEEE International Conference on Signal and Image Processing (ICSIP) · doi:10.1109/icsip52628.2021.9688773 · Cited by 2
“Among them, FR-IQA indicators in this paper include: feature-similarity (FSIM)[13], structural similarity (SSIM)[14]、multiscale-SSIM (MS-SSIM)[15], visual information fidelity (VIF)[16], peak signal-to-noise ratio (PSNR)[17], noise quality measure (NQM)[18], information fidelity criterion (IFC)[19], information conten…”
MethodMulti-Stage Gaussian Noise Reduction with Recurrent Neural Networks
Ranganath, A., DeGuchy, O., Singhal, M. K., et al. (2021) · 2018 52nd Asilomar Conference on Signals, Systems, and Computers · doi:10.1109/ieeeconf53345.2021.9723266 · Cited by 1
An Adaptive Hierarchical Concatenated Network With A Robust Loss Function For Image Denoising
Xiao, G., Wang, H., Shen, J., Chen, Z., & Zhang, Z. (2022) · Journal of Grid Computing · doi:10.1007/s10723-022-09601-6 · Cited by 1
“The parts can be substituted by multi-scale structural similarity (MS-SSIM) [36] and Laplace gradients on some special occasions.”
BackgroundMulti-feature Fusion With Attention and Receptive Field for Camouflaged People Detection
Chen, S., Zhang, W., Luo, J., Xiang, F., Zhan, J., & Wang, K. (2021) · China Automation Congress (CAC) · doi:10.1109/cac53003.2021.9728272 · Cited by 1
“where (k) bcedenote BCE loss [21], (k) s simdenote SSIM loss [22] and (k) iou denote IoU loss [23].”
BackgroundPhotoacoustic Tomography (PAT)
Wang, X., Yang, X., & Deán‐Ben, X. L. (2021) · MDPI eBooks · doi:10.3390/books978-3-03943-644-6 · Cited by 1
Image Quality Assessment of Tone Mapped Images
Lee, J., & Park, R. (2015) · International Journal of Computer Graphics & Animation · doi:10.5121/ijcga.2015.5202 · Cited by 1
Thanki, R. M., & Kothari, A. M. (2019) · Springer eBooks · doi:10.1007/978-3-030-12575-2_3 · Cited by 1
Towards an Efficient Facial Image Compression with Neural Networks
Spatafora, M. A. N., Ortis, A., & Battiato, S. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-06427-2_43 · Cited by 1
“…purpose of the training, we adopt the L1 loss, the Multi Scale Structural Similarity (MS-SSIM) as learning metric (it is a convenient way to incorporate image details at different resolutions [30] and it is suggested by the challenge [5]) and the following hyper-parameters: dynamic learning rate 0 .”
MethodQuality-Oriented Feature Regression for Robust Image Similarity Metric
Guo, J., Bao, Q., Zhu, R., Yang, W., & Liao, Q. (2022) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme52920.2022.9859721 · Cited by 1
“Structural similarity (SSIM) [2] and its variants [3, 4] were later proposed to extract and exploit structural information from images.”
BackgroundMethodTwo-stream spatiotemporal image fusion network based on difference transformation
Fang, S., Meng, S., Zhang, J., et al. (2022) · Journal of Applied Remote Sensing · doi:10.1117/1.jrs.16.038506 · Cited by 1
Multi-Metric Near-Optimal Image Denoising
Hara, K., & Inoue, K. (2022) · IntechOpen eBooks · doi:10.5772/intechopen.106710 · Cited by 1
Improved DC Estimation for JPEG Compression Via Convex Relaxation
Zhang, J., Chen, B., Huang, Y., et al. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897366 · Cited by 1
“We compare two methods in terms of PSNR, SSIM[16], MS-SSIM[17] and time cost.”
MethodSelf-citationEntropy-Reduced Attention for Image Compression
Wang, F., Chen, J., & Wang, R. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897669 · Cited by 1
“MSE (mean square error) and MS-SSIM (multiscale structural similarity)[23].”
MethodSIST: A Similarity Index for Storage Traffic
Pang, L., Kant, K., & Wu, J. (2022) · IEEE International Conference on Networking, Architecture and Storage (NAS) · doi:10.1109/nas55553.2022.9925320 · Cited by 1
“MS-SSIM [6] is a generalization of SSIM to multiple (resolution) scales, by successively applying a low pass filter (similar to using Haar Wavelet transform).”
MethodRudikov, S. I., Tsviatkou, V. Y., & Shkadarevich, A. P. (2022) · HERALD OF POLOTSK STATE UNIVERSITY Series С FUNDAMENTAL SCIENCES · doi:10.52928/2070-1624-2022-39-11-30-39 · Cited by 1
Robust Deep Support Vector Data Description for Unreliable Data
Le-Gia, T., Yi, D., & Ahn, J.-H. (2022) · IEEE/ACIS International Conference on Big Data, Cloud Computing, and Data Science (BCD) · doi:10.1109/bcd54882.2022.9900580 · Cited by 2
“The Mean Structural Similarity Index Measure (MSSIM) [14] measures the similarity between two images.”
BackgroundMedical Image Lossy Compression With LSTM Networks
Nithin Prabhu, G., Nagavi, T. C., & Mahesha, P. (2022) · IGI Global eBooks · doi:10.4018/978-1-6684-7544-7.ch027 · Cited by 1
A QoE Prediction Model Combining Network Parameters and Video Quality
Zhao, J., Li, S., & Hu, F. (2022) · doi:10.1109/cost57098.2022.00016 · Cited by 1
Geng, Y., & Zhou, W. (2022) · Chinese Control Conference (CCC) · doi:10.23919/ccc55666.2022.9901818 · Cited by 1
End-to-End Single-Frame Image Signal Processing for High Dynamic Range Scenes
Dinh, K. Q., & Choi, K. P. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00248 · Cited by 5
“In addition to visual inspection, we verify those methods in terms of objective quality measured in well-known metrics of PSNR, SSIM [33], MSSSIM [34], and FSIM [40] regarding the labels of multi-frame merge images [12] in Table 2.”
MethodStereo image quality assessment using deformed pixels and Sobel magnitude
Seghir, Z. A., Djezzar, M., Hemam, M., Zeggari, A., & Hachouf, F. (2023) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-223375 · Cited by 1
“To illustrate the performance of the proposed method SGSDM, we compare it with 21 state-of-the-art measures, including Benoit [11], Hewage [12], You[13],Gorley[14],Shen[15],Yang[16],Zhu[17], Akhter[18],Hachicha[19],PSNR,SSIM[5],MS-SSIM[37],Messai01[25],Messai02[27],Jianwei20 [30],KELM[36],Jianwei22[29],R3DQAE[32], MO-…”
ADIU:An Antiquarian Document Image Unwarping Dataset
Liu, S., & Liu, K. (2022) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata55660.2022.10020521 · Cited by 1
Sarvade, V. P., & Kulkarni, S. A. (2022) · International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS) · doi:10.1109/csitss57437.2022.10026385 · Cited by 2
Forensic sketch-to-photo transformation with improved Generative Adversarial Network (GAN)
Khatoon, S., & Umar, M. S. (2022) · International Conference on Multimedia, Signal Processing and Communication Technologies (IMPACT) · doi:10.1109/impact55510.2022.10029068 · Cited by 1
“We use three widely used metrics to quantitatively assess the proposed method: Structural Similarity Index Measure (mSSIMm) [24], Multi-scale Structural Similarity Index Measure (mMS-SSIMm) [25], and peak signal-to-noise ratio (mPSNRm).”
MethodThe impact of gas corrosion testing on the gray scale value of the security camera
Wang, T. (2023) · International Conference on Precision Instruments and Optical Engineering (PIOE) · doi:10.1117/12.2667328 · Cited by 1
Benda, V., Kubíček, J., Madeja, R., Oczka, D., Černý, M., & Dostálová, K. (2023) · Journal of Clinical Medicine · doi:10.3390/jcm12062138 · Cited by 1
“Structural similarity index [31] or SSIM index is a metric for the objective evaluation of two images containing the same overall structures, which are defined by their contrast, shape and luminance.”
BackgroundFast H.266/VVC intra-coding by mode inheritance
Chen, J., & Su, J.-A. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14849-5 · Cited by 1
“In addition, a Multi-Scale SSIM [18] was proposed to provide a more stable and flexible similarity measurement metric than the single-scale SSIM.”
BackgroundMethodInfluentialWu, Y., & Sheng, Y. (2022) · China Automation Congress (CAC) · doi:10.1109/cac57257.2022.10055291 · Cited by 2
Survey on measures of image similarity applied in image inpainting base on deep learning
He, L., Qiang, Z., Wu, Y., et al. (2022) · International Conference on Algorithms, Computing and Artificial Intelligence (ACAI) · doi:10.1145/3579654.3579737 · Cited by 1
Multi-Task Learning Approach Using Dynamic Hyperparameter for Multi-Exposure Fusion
Im, C.-G., Son, D.-M., Kwon, H., et al. (2023) · Mathematics · doi:10.3390/math11071620 · Cited by 1
Binocular Rivalry Impact on Macroblock-Loss Error Concealment for Stereoscopic 3D Video Transmission
Hasan, M. M., Hossain, M. A., Alotaibi, N., Arnold, J. F., & Azad, A. (2023) · Sensors · doi:10.3390/s23073604 · Cited by 1
“We used an MSE-, PSNR-, MS-SSIM-, and NIQE-based technique to estimate the objective testing for network packet loss in videos.”
MethodInfluentialLi, X., Lu, Y., Guo, Y., et al. (2022) · IEEE International Conference on Embedded and Ubiquitous Computing (EUC) · doi:10.1109/euc57774.2022.00017 · Cited by 1
“L MS-SSIM can validly preserve the high-frequency structural information of the image.”
MethodInfluentialOptimizing Video Compression With CNN-Based Autoencoders With Chroma Subsampling
Ghassab, V. K., Gonsalves, R., Mathur, S., et al. (2023) · SMPTE Motion Imaging Journal · doi:10.5594/jmi.2023.3245675 · Cited by 1
Development of image super-resolution framework
Shekar, S., Deepthi, K., Rahul, D., Dhawan, K., & Hegde, V. V. (2023) · IAES International Journal of Robotics and Automation (IJRA) · doi:10.11591/ijra.v12i2.pp179-183 · Cited by 1
Das, A. K., Patidar, V., & Naskar, R. (2023) · 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS) · doi:10.1109/icaccs57279.2023.10112738 · Cited by 1
“These are Structural Similarity Index Measure (SSIM) [36] and Learned Perceptual Image Patch Similarity (LPIPS) [37].”
MethodInfluentialDewarping Documents Using C2 Continuous Boundary Estimation
Mondal, P., Pant, A., & Soni, S. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095307 · Cited by 1
“The quantitive evaluation is done based on multi-scale structural similarity (MS-SSIM) [22] and the local distortions (LD) [15].”
MethodDO-FAM: Disentangled Non-Linear Latent Navigation For Facial Attribute Manipulation
Yuan, Y., Ma, S., Shan, H., et al. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095959 · Cited by 1
“Table 1 presents a quantitative comparison using MS-SSIM [23], Fr ´ echet Inception Distance (FID) [24], pixel-wise L 2 distance, LPIPS [18], as well as the identity similarity measured through CurricularFace [25].”
MethodReal Image Deblurring Based on Implicit Degradation Representations and Reblur Estimation
Zhao, Z., Qin, M., Gou, H., et al. (2023) · Applied Sciences · doi:10.3390/app13137738 · Cited by 1
Self-citationGround Penetrating Radar Disease Image Sample Generation Method Based on ConSinGan Model
马, 德. (2023) · Software Engineering and Applications · doi:10.12677/sea.2023.123054 · Cited by 1
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.