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. -
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 5,201–5,300 of 6,047
Oriole: Thwarting Privacy against Trustworthy Deep Learning ModelsPreprint
Chen, L., Hu, W., Zhao, B. Z. H., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.11502
“Next, the calculation of a cloak δ ( x, x T i ) is defined as: where δ subjects to | δ ( x, x T i ) | ρ , and | δ ( x, x T i ) | is calculated by DSSIM (Structure Dis-Similarity Index) [42, 44] and ρ is the perturbation budget.”
MethodGeneralizable Limited-Angle CT Reconstruction via Sinogram ExtrapolationPreprint
Wang, C., Zhang, H., Li, Q., et al. (2021) · arXiv (Cornell University)
Event-based Synthetic Aperture ImagingPreprint
Zhang, X., Wei, L., Yu, L., et al. (2021) · arXiv (Cornell University)
Virtual Reality: A Survey of Enabling Technologies and its Applications in IoTPreprint
Hu, M., Luo, X., Chen, J., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.06472
“To rectify this, multi-scale, structure similarity (MS-SSIM) has also been defined [97].”
MethodLearning a No Reference Quality Assessment Metric for Encoded 4K-UHD Video
Xu, J., Dong, Y., Song, L., et al. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-1194-0_28
Distributed Video Adaptive Block Compressive SensingPreprint
Zammit, J. A., & Wassell, I. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.00636
“The first seventeen frames of VidSet6 were used with the seventeenth frame used by VFI to compute key frames in the second GOP, but PSNR and MS-SSIM [26] results are only reported for the luminance (Y) plane of the first sixteen frames.”
MethodLearning Semantic-Aware Dynamics for Video PredictionPreprint
Bei, X., Yang, Y., & Soatto, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.09762
“Higher MS-SSIM scores and lower LPIPS distances suggest better performance.”
MethodInfluentialDewarping Document Image By Displacement Flow Estimation with Fully Convolutional NetworkPreprint
Xie, G.-W., Yin, F., Zhang, X.-Y., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.06815
“One of them is Multi-Scale Structural Similarity (MS-SSIM) [22] which evaluate the global similarity between the rectified document images and scanned images in multi-scale.”
BackgroundMohammed, U. S., Omer, O. A., & Hamed, A. A. (2016) · JES. Journal of Engineering Sciences/JES. Journal of engineering sciences · doi:10.21608/jesaun.2016.117626
Improving precision of objective image/video quality metricsPreprint
Behzadpour, M., & Ghanbari, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.12448
“They include: SSIM [3], IW-SSIM [5], MS-SSIM [4], VSI [7], FSIM [8], FSIMc [8], SPSIM [9], EFS [10] and GMSD [11].”
BackgroundMethodInfluentialLearning to Learn to CompressPreprint
Zou, N., Zhang, H., Cricri, F., Tavakoli, H. R., Lainema, J., Hannuksela, M. M., Aksu, E., & Rahtu, E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.16054 · Cited by 1
“In the first stage, a conventional training session is performed to achieve generalization, by using the following rate-distortion loss: L(x̂, x, z, τ) = λd1Ld1(x̂, x) + λd2Ld2(x̂, x) + λd3Ld3(x̂, x) + λrLr(z) + λmM(τ), (7) where Ld1 is the negative multi-scale structural similarity (MS-SSIM) [25], Ld2 is the mean-squ…”
BackgroundInfluentialDeep Convolutional Neural Network for Non-rigid Image RegistrationPreprint
Durech, E. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.12034
“the structural similarity between two windows, x and y, as [12, 13]”
BackgroundPredicting Surface Reflectance Properties of Outdoor Scenes Under Unknown Natural Illumination
Wasee, F. R., Joy, A., & Poullis, C. (2022) · IEEE Computer Graphics and Applications · doi:10.1109/mcg.2022.3151010
“We report our results on the following threemetrics: 1) peak signal-to-noise ratio (PSNR); 2) normalized root-mean-squared error (NRMSE); 3) structural dissimilarity index (DSSIM), which unlike RMSE or PSNR which only calculate the errors among pixels, utilizes structural information by assuming that pixels have stron…”
MethodLearning to Generate Novel Scene Compositions from Single Images and VideosPreprint
Sushko, V., Gall, J., & Khoreva, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.05847 · Cited by 4
“Image diversity is assessed by the average LPIPS [3] and MS-SSIM [14] across pairs of generated images.”
FOANet: A Focus of Attention Network with Application to Myocardium Segmentation
Zhao, Z., Puybareau, É., Boutry, N., et al. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412016
“To obtain high quality regional segmentation and nice boundaries, we define ` as a hybrid loss: ` = `CCE+`SSIM+`DC, where `CCE, `SSIM and `DC respectively denote CCE loss [15], SSIM loss [16] and DC loss [17] respectively.”
BackgroundMethodEvaluating Foveated Video Quality Using Entropic DifferencingPreprint
Jin, Y., Patney, A., & Bovik, A. C. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.06817
“We compared FED with several leading existing IQA algorithms on both the 2D and 3D LIVE-FBT-FCVR databases: PSNR [20], SSIM [20], MS-SSIM [21], VIF [13], S-RRED [16], SpeedIQA [17], FSIM [22], FWQI [9], and FA-SSIM [11].”
MethodSelf-citationTracking-based rolling angles recovery method for holographic tomography of flowing cellsPreprint
Pirone, D., Memmolo, P., Merola, F., et al. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.06.01.446558
Subjective Opinions Matter: Controllable Image Quality Assessment Using Pseudo Reference ImagesPreprint
Guo, J., Wang, W., Yang, W., Liao, Q., & Zhou, J. (2021) · arXiv (Cornell University)
Tong, W., Shen, Z., Chu, X. Y., et al. (2021) · International Conference on Communications, Information System and Computer Engineering (CISCE) · doi:10.1109/cisce52179.2021.9445875
Where is the disease? Semi-supervised pseudo-normality synthesis from an abnormal imagePreprint
Du, Y., Quan, Q., Han, H., & Zhou, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.15345 · Cited by 2
“where MS−SSIM stands for multiscale structural similarity [25].”
BackgroundHierarchical Temporal Structure for End-to-End Neural Network-based Video Compression
Bégaint, J., Racapé, F., Feltman, S., et al. (2021)
Deep Learning for Robust Super-resolution
Molahasani, M. (2021)
Image restoration quality assessment based on regional differential information entropyPreprint
Wang, Z., Zhuang, J., Xu, N., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.03642
“Wang proposed the MS-SSIM [9] based on multi-scale structural similarity comparisons.”
MethodInfluentialSelf-citationNo-Reference Quality Assessment for Colored Point Cloud and Mesh Based on Natural Scene StatisticsPreprint
Zhang, Z., Sun, W., Min, X., et al. (2021) · arXiv (Cornell University)
Multitask Identity-Aware Image Steganography via Minimax OptimizationPreprint
Cui, J., Zhang, P., Li, S., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.05819
Del-Net: A Single-Stage Network for Mobile Camera ISPPreprint
Gupta, S., Srivastava, D., Chaturvedi, U., Jain, A., & Khandelwal, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.01623 · Cited by 7
Stereo Waterdrop Removal with Row-wise Dilated AttentionPreprint
Shi, Z., Fan, N., Yeung, D., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.03457
“To quantitatively evaluate our method, we use the standard PSNR, MS-SSIM [29], and LPIPS [45] as the metrics.”
Perceptually Dithered HDR for 8-Bit Interfaces
Atkins, R., Wanat, R., & Pytlarz, J. (2021) · SMPTE Motion Imaging Journal · doi:10.5594/jmi.2021.3087824
On Designing Deep Learning Approaches for Classification of Football Jersey Images in the Wild
Matta, R. R. (2017) · The Research Repository @ WVU (West Virginia University) · doi:10.33915/etd.6178
Visual Boundary Knowledge Translation for Foreground SegmentationPreprint
Feng, Z., Cheng, L., Wang, X., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.00379
“Qin et al. (2019) adopted the patchlevel SSIM loss (Wang, Simoncelli, and Bovik 2003) to assign higher weights to the boundary.”
MethodShi, R., Wang, W., Li, Z., He, L., Sheng, K., Ma, L., Du, K., Jiang, T., & Huang, T. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.05.30.446334
Convex Optimization Method for Quantifying Image Quality Induced Saliency Variation
Guo, P., Zhao, X., Wu, D., Zhang, L., Zeng, D., & Liu, H. (2021) · IEEE Access · doi:10.1109/access.2021.3102465
“Since saliency maps are essentially images, we naturally wonder whether the well-established image fidelity metric Structural SIMilarity (SSIM) index [27] and its variants [28]–[30] could be used to evaluate the distortion-induced saliency variation.”
MethodLossy Medical Image Compression using Residual Learning-based Dual Autoencoder ModelPreprint
Mishra, D., Singh, S. K., & Singh, R. K. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.10579
“The proposed algorithm has been evaluated for the quality of reconstructed images with the help of peak signal-to-noise ratio (PSNR) [22] and multi-structural similarity (MS-SSIM) [23].”
MethodBlockiness Distortion Measurement for Intra-Coded Video Frames by Using an Efficient NR Algorithm
Uzair, M. (2021) · International Conference on Electronics, Computers and Artificial Intelligence (ECAI) · doi:10.1109/ecai52376.2021.9515167
Document Dewarping with Control PointsPreprint
Xie, G.-W., Yin, F., Zhang, X.-Y., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.10543
“MS-SSIM evaluates the global similarity between the rectified image and scanned image in multi-scale.”
MethodTian, Y., Liu, F., Pang, G., Chen, Y., Liu, Y., Verjans, J. W. H., Singh, R., & Carneiro, G. (2021) · arXiv (Cornell University)
Quality assessment of 3D synthesized images based on structural and textural distortion
Fatima, T., & Farid, M. S. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11382-1
“To estimate the texture quality, the region around the edges of the source and the warped images are compared using block based MSSIM metric.”
BackgroundMethodInfluentialTowards More Powerful Multi-column Convolutional Network for Crowd Counting
Zhang, J., Chu, Q., Li, W., et al. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87355-4_32
Efficient Depth-Included Residual Refinement Network for RGB-D Saliency Detection
Yu, J., Yan, G., Xu, X., Wang, J., Chen, S., & Hu, X. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-87361-5_1
Çok bantlı görüntülerde pan-keskinleştirme üzerine bir inceleme
Yılmaz, Ç. Ş., YILMAZ, V., & Güngör, O. (2021) · Gümüşhane Üniversitesi Fen Bilimleri Enstitüsü Dergisi · doi:10.17714/gumusfenbil.972014
Degraded Reference Image Quality AssessmentPreprint
Athar, S., & Wang, Z. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.14899
“many combinations of FR methods (PSNR, MSSSIM [29],”
MethodInfluentialSelf-citationA Light SRGAN for Up-Scaling of Low Resolution and High Latency Images
Ghosh, A., Goswami, K., Chatterjee, R., & Sarkar, P. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-81462-5_6
Full-reference Image Quality Metric For Computer-rendered Stereoscopic Images
Li, L., & Chen, C. (2021) · International Conference on Electronic Information Engineering and Computer Science (EIECS) · doi:10.1109/eiecs53707.2021.9587950
Related Work on Image Quality AssessmentPreprint
Wang, D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.06291
Li, K., Ma, X., Ni, R., et al. (2020) · International Robotics & Automation Journal · doi:10.15406/iratj.2020.06.00203
The Impact of the Transmission Pulse Shape in Ultrasound Harmonic Imaging
Zhou, M., Chen, P., Mischi, M., et al. (2021) · IEEE International Ultrasonics Symposium · doi:10.1109/ius52206.2021.9593335
“The structural similarity (SSIM) index [13] referred to the images with sinewave excitations, and the contrast-to-noise ratio (CNR) between the region of interest (ROI) and the background, are used to assess the image quality for each cyst separately [14], and as shown for each case in Fig.”
MethodCompressing Sensor Data for Remote Assistance of Autonomous Vehicles using Deep Generative ModelsPreprint
Bogdoll, D., Jestram, J., Rauch, J., Scheib, C., Wittig, M., & Zöllner, J. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.03201 · Cited by 12
“For the evaluation of the image reconstruction quality, the metrics MSE, LPIPS, peak signal to noise ratio (PSNR) and multiscale structural similarity index measure (MS-SSIM) [51] are taken into account.”
Human Imperceptible Attacks and Applications to Improve FairnessPreprint
Hua, X., Xu, H., Blanchet, J., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.15603
“Traditional IQA methods include SSIM [62], MS-SSIM [63] FSIM [73], and PSNR [37].”
MethodSaliency Enhancement using Superpixel Similarity.Preprint
João, L., & Falcão, A. X. (2021) · arXiv (Cornell University)
MSANet: multi-scale attention guided deep neural network for blind image quality assessment
Ma, X., & Wang, J. (2021) · International Conference on Industrial IoT, Big Data and Supply Chain (IIoTBDSC) · doi:10.1117/12.2624147
EStarGAN: Enhanced StarGAN for Multi-Style High-Definition Image Translation
Zhang, X., Yang, M., & Chai, H. (2021) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc52423.2021.9659053 · Cited by 1
“[27] further proposed the MS-SSIM after observing that the analysis of structural influences at different scales also has benefits for visual evaluation.”
MethodJiao, Y., He, Y. R., Kandel, M. E., Liu, X., Lu, W., & Popescu, G. (2021) · Default Digital Object Group · doi:10.1063/5.0041901.1
Defending Against Attacks Tailored to Transfer Learning Via Feature DistancingPreprint
Ji, S., Park, N., Na, D., et al. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3993063
Jiao, Y., He, Y. R., Kandel, M. E., Liu, X., Lu, W., & Popescu, G. (2021) · Default Digital Object Group · doi:10.1063/5.0041901.2
A Surface Roughness Measurement Method Based on Color Image Euclidean Distance
Zhao, X., Zhao, M., Ji, J., et al. (2021) · International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD) · doi:10.1109/icsmd53520.2021.9670829
Capsule Network based Super Resolution Method for Medical Image Enhancement
Munasingha, S. C., & Fernando, S. (2021) · IEEE International Conference on Signal and Image Processing (ICSIP) · doi:10.1109/icsip52628.2021.9688948
“For this, several image quality assessment indexes have been used; PSNR, SSIM [30], MSSSIM[31] and UIQ[32].”
MethodUncertainty Quantification And Sensitivity Analysis Of Parameterization-free Surrogate ModelPreprint
Cao, J., Li, Q., Xu, L., Yang, R., & Dai, Y. (2022) · Preprints.org · doi:10.20944/preprints202104.0762.v3
“3.3), the performance of surrogate model305 is also evaluated by three different metrics: • Mean squared error is used to measure the average of pixel-wise error between the model prediction contour (Yi) and the ground truth contour (Ŷi); • SSIM is used to evaluate the structure similarity level between the model310…”
MethodInfluentialTwo-Step Image-in-Image Steganography via GAN
Wu, G., Yu, X., Liang, H., & Li, M. (2022) · International Journal of Digital Crime and Forensics · doi:10.4018/ijdcf.295814 · Cited by 1
“Our algorithm has improvement in both SSIM and PSNR.”
MethodInfluentialAN EFFECTIVE FOVEATED 360° IMAGE ASSESSMENT BASED ON GRAPH CONVOLUTION NETWORKPreprint
Hương, T. T., Thu, H. D., Tran, T. T. H., Truong, T. Q., Ngoc, N. P., Nguyen, T., Ngo, V. B., & Bui, T. (2022) · doi:10.36227/techrxiv.19134935
(2021) · Wiley eBooks · doi:10.1002/9781119646181.biblio
Stereoscopic Image Quality Assessment
Ding, Y. S. (2018) · Springer eBooks · doi:10.1007/978-3-662-56497-4_7
AN EFFECTIVE FOVEATED 360° IMAGE ASSESSMENT BASED ON GRAPH CONVOLUTION NETWORKPreprint
Hương, T. T., Thu, H. D., Tran, T. T. H., Truong, T. Q., Ngoc, N. P., Nguyen, T., Ngo, V. B., & Bui, T. (2022) · doi:10.36227/techrxiv.19134935.v1
INTELLIGENT STYLE TRANSFER OF FILM IMAGE BASED ON CYCLEGAN
Liu, D., & Wu, H. W. A. B. (2020) · doi:10.33965/cgv2020_202011l006
“In order to improve the quality of the final generated image on the basis of SSIM loss, we chose MS-SSIM loss (Wang et al., 2003).”
MethodLossy Compression of Remote Sensing and Dental Images Corrupted by Spatially Correlated Noise
Лукин, В. В., Krivenko, S., Kaluzhinov, I., et al. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-030-94259-5_77
Unsupervised Blind Image Quality Assessment based on Multi-Feature Fusion
He, Q., Yang, C., & An, P. (2022) · International Conference on Embedded Systems and Applications (EMSA) · doi:10.5121/csit.2022.120627
LA-U2Net: location-aware U2Net for salient object detection
Huang, X., LI, J., Ding, Y. F., et al. (2022) · Eighth Symposium on Novel Photoelectronic Detection Technology and Applications · doi:10.1117/12.2623043
“l iou = − ∑H r= ∑W c=Y(r, c)P(r, c) ∑H r= ∑W c=[Y(r, c) + P(r, c)−Y(r, c)P(r, c)] (10)”
Encoding and Decoding of Picture Embedded barcodes by Threshold
Ieswaria, S., Bhavani, R., & Priya, R. (2022) · International Conference on Computing Methodologies and Communication (ICCMC) · doi:10.1109/iccmc53470.2022.9754062
“The method provided a better Structural Similarity Index Measure (SSIM)[23], MSSSIM and PSNR.”
BackgroundMadmad, T., Libertiaux, V., & Vleeschouwer, C. D. (2022) · doi:10.1117/12.2612661
“The first term of the TMQI is based on the Structural Similarity Index Metric (SSIM) in its multi-scale version.(34) This part mainly aims to encourage the structural similarity between the two images taken as input.”
MethodKim, K., Lim, C. Y., & Chung, M. J. (2022) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi52829.2022.9761642 · Cited by 1
“where x̂i = Gθ∗(z) denotes the trained generator’s output for the i-th slice estimate, Lssim(·) denotes the structural similarity function [23], Ltv(·) is the total variation loss, and x0 denotes a noisy estimation of the actual i-th slice xi.”
BackgroundPrime Knowledge with Local Pattern Consistency for Knowledge Distillation
Tang, Q., Xu, X., & Wang, J. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746534
Non-Mydriatic Fundus Images Enhancement Based on Conformal Mapping Extension
Yan, S., Chen, X., Sun, J., et al. (2021) · IEEE International Conference on Cloud Computing and Intelligent Systems (CCIS) · doi:10.1109/ccis53392.2021.9754644
A Brand-New Method to Solve Rotated Template Matching Using Metaheuristic Algorithms and SsimPreprint
González, A., Corona, G., Maciel-Castillo, O., et al. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4073663
A continuous bitstream-based blind video quality assessment using multi-layer perceptron
Merly, H., Ninassi, A., & Charrier, C. (2022) · Electronic Imaging · doi:10.2352/ei.2022.34.9.iqsp-319
Cbir-Gan: A Triplet Generative Adversarial Network for Content-Based Image RetrievalPreprint
Norouzi, N., Zarvani, M., Moghadam, S. S. T., & Azmi, R. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4057354 · Cited by 1
Technology, Science and Culture: A Global Vision, Volume III
Hernández, L. R., & Meneses, M. A. S. (2022) · IntechOpen eBooks · doi:10.5772/intechopen.99973
A Biologically-Inspired Approach to Making HDR Video Quality Assessment Easier
McCarthy, S. T. (2016) · SMPTE Annual Technical Conference and Exhibition · doi:10.5594/m001679
Quality Assessment of Video in Digital Television
Fonseca, R., & Ramírez, M. A. (2015) · SET INTERNATIONAL JOURNAL OF BROADCAST ENGINEERING · doi:10.18580/setijbe.2015.1
Spatial and Temporal Analysis Considering Relevant Regions Applied to Video Quality Assessment
Oliveira, Í. D. P., Cardoso, J. V. D. M., Regis, C. D. M., & de Alencar, M. S. (2013) · doi:10.14209/sbrt.2013.160 · Cited by 1
(2019) · International Journal of Innovative Technology and Exploring Engineering · doi:10.35940/ijitee.f1071.0486s419
Realistic Image-to-Image Translation with Enhanced Texture
Duan, G., Gong, Y., Zhao, H., Ma, W., Song, D., Ma, Z., & Xie, M. (2021) · Asia Symposium on Signal Processing (ASSP) · doi:10.1109/assp54407.2021.00010
Similarity and symmetry measures based on fuzzy descriptors of image objects’ composition
Marcin Iwanowski, C., & Grza̧bka, M. (2021) · Computer Science Research Notes · doi:10.24132/csrn.2021.3101.33
Xu, L., Lin, W., & Kuo, C. ‐. J. (2015) · Springer briefs in electrical and computer engineering · doi:10.1007/978-981-287-468-9_5
A CBCT image noise reduction method based on cGANPreprint
Miao, Y., Ding, Y., Zhu, X., et al. (2020) · doi:10.21203/rs.3.rs-19128/v1
Perceptually Correlated Image Quality Metrics
Phillips, J. B., & Eliasson, H. (2017) · Wiley eBooks · doi:10.1002/9781119054504.ch7
Vicode: 3D Barcode with Embedded Video Using Histogram Shifting Based Reversible Data Hiding
(2017) · International Journal of Science and Research (IJSR) · doi:10.21275/5071708
Adversarial net and its variants
Du, C., Huang, Y., & Zeng, H. (2022) · International Conference on Applied Mathematics, Modelling and Intelligent Computing (CAMMIC) · doi:10.1117/12.2639238
“MS-SSIM [18] is an improved version by introducing multi-scale quality assessment into the measurement.”
MethodManimala, G., Kavitha, P., Lekha, C., et al. (2022) · International Conference on Communication, Computing and Internet of Things (IC3IoT) · doi:10.1109/ic3iot53935.2022.9767983
“[7] : The shortcomings of Generative Adversarial Networks (GAN) have been analyzed and to solve that problem, they propose a Super-Resolution Generative Adversarial Networks with Ranker (RankSRGAN) to upgrade the performance of generator as per the incessant metrics.”
BackgroundA Weakly Supervised Deep Generative Model for Complex Image Restoration and Style TransformationPreprint
Dai, W., Wong, I. H. M., & Wong, T. T. W. (2022) · doi:10.36227/techrxiv.19747057
Study on Generation of Picture Barcodes based on Encoding and Decoding Techniques
Ieswaria, S., Bhavani, R., & Priya, R. (2022) · International Conference on Trends in Electronics and Informatics (ICOEI) · doi:10.1109/icoei53556.2022.9776738
Bi, Z., Wu, X., Li, Z., et al. (2022) · doi:10.5194/gmd-2022-117-rc2
Bi, Z., Wu, X., Li, Z., et al. (2022) · doi:10.5194/gmd-2022-117-rc1
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.