The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index; none of the 14 sources its claims cite is checked for support yet.
Multiscale structural similarity for image quality assessment
Abstract
The structural similarity image quality paradigm is based on the assumption that the human visual system is highly adapted for extracting structural information from the scene, and therefore a measure of structural similarity can provide a good approximation to perceived image quality. This paper proposes a multiscale structural similarity method, which supplies more flexibility than previous single-scale methods in incorporating the variations of viewing conditions. We develop an image synthesis method to calibrate the parameters that define the relative importance of different scales. Experimental comparisons demonstrate the effectiveness of the proposed method.
Overview
CoChat Summary
TL;DR
This paper proposes a multi-scale structural similarity (MS-SSIM) image quality method that combines contrast and structure comparisons across scales and luminance comparison at the coarsest scale. On the LIVE JPEG/JPEG2000 database, MS-SSIM outperformed PSNR, the Sarnoff model, and single-scale SSIM variants on all reported evaluation criteria.
Key findings
- MS-SSIM achieved the best reported performance: CC 0.969, ROCC 0.966, MAE 3.86, RMS 4.91, and OR 1.16%, compared with the best single-scale SSIM at M=2 (CC 0.963, ROCC 0.959, MAE 4.21, RMS 5.38, OR 2.62%) and PSNR (CC 0.905, ROCC 0.901, MAE 6.53, RMS 8.45, OR 15.7%).
- Single-scale SSIM performance varied with scale; the best single-scale result was at M=2, and single-scale SSIM tended to give higher scores as scale increased.
- The calibrated cross-scale exponents were β1=γ1=0.0448, β2=γ2=0.2856, β3=γ3=0.3001, β4=γ4=0.2363, and α5=β5=γ5=0.1333.
- The authors conclude that multi-scale SSIM provides a meaningful balance between scales and outperforms the best single-scale SSIM and state-of-the-art image quality metrics.
Methods
- The MS-SSIM system iteratively applies a low-pass filter and downsamples by 2; at each scale it computes contrast and structure comparisons, computes luminance comparison only at Scale M, and combines them using exponents normalized so that ∑γj=1.
- Cross-scale parameters were calibrated by image synthesis: 5 scales and 12 distortion levels (range 2^3 to 2^14) were used with 10 original 64×64 images, producing 600 distorted images; 8 subjects selected images of equal perceived quality across scales at a viewing distance of 32 pixels per degree of visual angle.
- Evaluation used the LIVE database with 344 JPEG and JPEG2000 compressed images (bit rate 0.028 to 3.150 bits/pixel), MOS from 13–25 subjective scores, and compared PSNR, Sarnoff JNDmetrix 8.0, single-scale SSIM for M=1–5, and MS-SSIM using CC, MAE, RMS, OR, and ROCC after logistic mapping.
Limitations
- Stated: the image-synthesis calibration approach is “still rather crude,” and the authors are working on a more systematic approach.
- Stated: CSF cannot be directly used to derive the parameters because it is typically measured at visibility threshold with simplified stimuli, whereas the goal is comparing complex structured images at visible distortion levels.
- Evident from the text: calibration used only 10 original 64×64 grayscale images and 8 subjects, including one author, and evaluation was limited to the LIVE JPEG/JPEG2000 database.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 Valid · 1 Not valid · 14 Not checked · 18 Own results and interpretations
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It can also be observed that the single-scale model tends to supply higher scores with the increase of scales.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Finally, for every one of the objective evaluation criteria, multi-scale SSIM model outperforms all the other models, including the best single-scale SSIM model, suggesting a meaningful balance between scales.”
- Also stated in: § 5. DISCUSSIONS · p. 4 · hedged
“Experiments show that with an appropriate parameter settings, the multi-scale method outperforms the best single-scale SSIM model as well as state-of-the-art image quality metrics.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 5. DISCUSSIONS · p. 4 · hedged
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In general, the subjects agreed with each other on each image more than they agreed with themselves across different images.”
plainstates an associationn = 8- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The resulting parameters we obtained are β 1 = γ 1 = 0.0448, β 2 = γ 2 = 0.2856, β 3 = γ 3 = 0.3001, β 4 = γ 4 = 0.2363, and α 5 = β 5 = γ 5 = 0.1333, respectively.”
plainn = 8- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“However, the SSIM index algorithm introduced in [5] is a single-scale approach.”
What the sources say
- Not matchedcites [5] [5] Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, 'Image quality assessment: From error measurement to structural similarity,' IEEE Trans. Image Processing , vol. 13, Jan. 2004. -
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
10 more claims
Create a free account to see all 33 claims and every source verdict.
- It may state two separate claims as one. 8
- Probably not a substantial claim. 13
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Further, as research in quality assessment has demonstrated, incorporating multiscale information when assessing quality produces QA algorithms that perform better in terms of correlation with human perception [13], [29].”
From No-Reference Image Quality Assessment in the Spatial Domain (2012) · cites this paper as [13]
Citations
Cites
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892
Self-citationA universal image quality index
Wang, Z., & Bovik, A. C. (2002) · IEEE Signal Processing Letters · doi:10.1109/97.995823 · Cited by 5,757
Self-citationImage quality measures and their performance
Eskicioglu, A. M., & Fisher, P. S. (1995) · IEEE Transactions on Communications · doi:10.1109/26.477498 · Cited by 2,117
A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients
Portilla, J., & Simoncelli, E. P. (2000) · International Journal of Computer Vision · doi:10.1023/a:1026553619983 · Cited by 1,806
Self-citation(1995) · Medical Entomology and Zoology · Cited by 1,212
Pyramid-based texture analysis/synthesis
Heeger, D. J., & Bergen, J. R. (1995) · Proceedings of the 22nd annual conference on Computer graphics and interactive techniques - SIGGRAPH '95 · doi:10.1145/218380.218446 · Cited by 1,095
Video quality assessment based on structural distortion measurement
Wang, Z., Lu, L., & Bovik, A. C. (2004) · Signal Processing: Image Communication · doi:10.1016/s0923-5965(03)00076-6 · Cited by 1,024
Self-citationImage Quality Assessment: From Error Measurement to Structural Similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · Cited by 881
Self-citationTeo, P. C., & Heeger, D. J. (2002) · Proceedings of 1st International Conference on Image Processing · doi:10.1109/icip.1994.413502 · Cited by 471
Objective video quality assessment
(2003) · Handbook of Video Databases · doi:10.1201/9780203489864-45 · Cited by 359
Research works printed but not linked: 2
- 0, JNDmetrix Technology, Sarnoff Corporation
- 2000, Final report from the video quality experts group on the validation of objective models of video quality assessment, VQEG
Cited by
Items 5,401–5,500 of 6,047
TRICKVOS: A Bag of Tricks for Video Object Segmentation
Skartados, E., Georgiadis, K., Yucel, M. K., Koskinas, I., Domi, A., Drosou, A., Manganelli, B., & Saà-Garriga, A. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10222050 · Cited by 1
“For the former, a natural choice is the SSIM metric [12].”
BackgroundLiu, Y., & Zhang, L. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10222789
ЛОКАЛЬНО-АДАПТИВНА ФІЛЬТРАЦІЯ ЗОБРАЖЕНЬ З ВИКОРИСТАННЯМ ТЕТРОЛЕТ ПЕРЕТВОРЕННЯ
Рубель, А. С., & Lukin, V. P. (2017) · Aerospace technic and technology · doi:10.32620/aktt.2017.5.13
Phenotype-preserving metric design for high-content image reconstruction by generative inpainting
Sharma, V., & Yakimovich, A. (2023) · Emerging Topics in Artificial Intelligence (ETAI) · doi:10.1117/12.2676835
“One approach for circumventing this is to evaluate the metric on multiple scales.(26) Other approaches aim to introduce subjective quality assessment involving human judgement.”
A New Data Modeling Approach for Alignment-free Biological Applications
Vieira, D. M., de Armas, E. M., Guateque, M. L., et al. (2023) · doi:10.5753/sbbd.2023.232471
Dual-Level Blind Omnidirectional Image Quality Assessment Network Based on Human Visual Perception
Liu, D., Zhang, L., Wan, L., et al. (2023) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2023.01409112
“For FR type, the peak-signalto-noise ratio (PSNR) and the structural similarity index measure (SSIM) [1] are respectively adopted for OIQA [2, 3, 4, 5, 6].”
MethodFan, X., Peng, C., Jiang, X., et al. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4594539
Glancing Inside the Smartphone Camera: A Deep Insight into Image Signal Processing PipelinePreprint
Pal, A., Sehgal, P., & Bansal, R. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4594551
Image Super-Resolution Algorithm Based UAV Forensics Method
Peng, L. (2023) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc58118.2023.10270167 · Cited by 1
Hybrid Inverse Mapping Algorithm Based on Residual Iteration
Wei, W., & Zhou, X. (2023) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc58118.2023.10270402
Mejora de reconstrucción estéreo subacuática mediante caracterización de turbidez
Gómez, G. V., Torre‐Ferrero, C., García, J. R. L., et al. (2023) · doi:10.17979/spudc.9788497498609.017
A Client-Friendly Lightweight Privacy-Preserving Split Learning FrameworkPreprint
Chen, H., Wang, L., Zuo, L., & Liu, H. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4606662
Generating High-Resolution SAR Images with Loss Function Customization
Lee, J., Kim, J., Kim, J., et al. (2023) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss52108.2023.10282576
Generative Framework Approach to Match Landsat and Sentinel-2 Data
Roy, S., Sridhar, M., Mandel, J., et al. (2023) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss52108.2023.10281459
“Evaluations were made by visual inspection of the generated image, calculation root mean square error (RMSE) and structural similarity index measure (SSIM) [11].”
MethodLimited-Reference Image Quality Assessment: Paradigms and Discussions
Zhang, K. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3613436
“Given the great success of SSIM, several SSIM-based variants have been proposed, such as multi-scale SSIM [18] and information content weighted SSIM [16].”
MethodZhao, H., Sun, C., Shi, D., et al. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4615629
Optimization of ISP parameters for low light conditions using a non-linear reference based approach
Alai, S. R., & Bhat, R. (2023) · Electronic Imaging · doi:10.2352/ei.2023.35.8.iqsp-314
Data-driven Modelling of Cognitive and Affective Variables of Perception of Multimedia Content
Población, R. F.-C. (2023) · UPM Digital Archive (Technical University of Madrid) · doi:10.20868/upm.thesis.76521 · Cited by 1
FANs: fully attentional networks for image compression
Kong, W., Sun, M., & Xue, H. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17633-7
“PSNR and Multi-scale Structural Similarity Index (MS-SSIM) Measure [45], shows great potential for practical compression use and presents many works [6, 7, 32, 35, 38].”
Female or male observers ? - Gender differences in subjective image quality assessment
Mayel, F. E. E., Dahmouni, A., & Abdelouahad, A. A. (2023) · doi:10.1145/3607720.3607729
Attention-Guided HDR Reconstruction for Enhancing Smart City Applications
Chen, Y.-Y., Hsia, C., Jhong, S.-Y., & Lai, C. (2023) · Electronics · doi:10.3390/electronics12224625
Hash encoded neural radiance field with view-dependent mapping
Zhou, Y., & Cheng, W. (2023) · International Conference on Computer Graphics, Image and Virtualization (ICCGIV) · doi:10.1117/12.3008019
“Therefore, in the experiment, we referred to the experimental methods and metrics adopted by previous NeRF models, using a set of positions and directions data in a scene as input of the model, then comparing the 2D images output by the model with the ground truths, and measuring them in three metrics: Peak Signal-to-…”
MethodRehman, U., Ali, S. F., Chung, E. S., et al. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4635984
Learned video compression with channel-wise autoregressive entropy model
Yu, Y., He, X., Wu, X., et al. (2023) · Journal of Electronic Imaging · doi:10.1117/1.jei.32.6.063013
“We use a more powerful entropy model to remove spatio-temporal redundancy, and our framework achieves promising compression effects in PSNR and MS-SSIM metrics.”
MethodInfluentialMEDIGAN MODEL UPLOAD: 00023_PIX2PIXHD_BREAST_DCEMRIPreprint
Osuala, R. O., Joshi, S., Tsirikoglou, A., et al. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.10879
“The metric values alongside their standard deviation for (a) are PSNR ↑ =32.91(1.35), MS-SSIM ↑ =0.798(0.08), LPIPS ↓ =0.064(0.04), for (b) they are PSNR ↑ =32.42(1.68), MS-SSIM ↑ =0.780(0.07), LPIPS ↓ =0.084(0.05), and for (c) they resulted in PSNR ↑ =34.74(1.73), MS-SSIM ↑ =0.717(0.09), LPIPS ↓ =0.062(0.03).”
MethodInfluentialGoran, N., Begović, A., & Čolaković, A. (2023) · TEM Journal · doi:10.18421/tem124-10
Influence of sorting measures on similar segment grouping based denoising algorithms
Preethisree, G., Vivekanand, V., Mishra, D., et al. (2023) · Signal Image and Video Processing · doi:10.1007/s11760-023-02870-y
“An improved formofthismeasurethemultiscalestructuralsimilarityindex (MS-SSIM) computed as described in [32] is also used. where μ x , μ ˆ x , σ x , σ ˆ x are the mean and variance of x and ˆ x , respectively. σ x ˆ x is the covariance between x and ˆ x . c 1 and c 2 are finite constants.”
Semantic Image Translation for Repairing the Texture Defects of Building Models
Shang, Q., Hu, H., Yu, H., Xu, B., Wang, L., & Zhu, Q. (2023) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2023.3338962
“2) Quantitative Comparison: Peak signal-to-noise ratio (PSNR) and SSIM are widely used indexes for image quality evaluation [81].”
MethodYan, Z., Xu, J., He, H., et al. (2023) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp59012.2023.10337667
“…we report the results of quantitative comparisons among our ADC-GInv and existing baselines in Table 1, in terms of the widely employed metrics in evaluating the reconstruction quality, including mean squared error (MSE), LPIPS [12] and multi-scale structural similarity (MS-SSIM) [19] metrics.”
MethodDeep Fusion Network Based Sparse View CT Reconstructions for Clinical Diagnostic Scanners
Xu, Y., Li, J., & Lin, H. (2023) · Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/embc40787.2023.10341175
“The proposed network uses a custom loss which is a combination of mean square error(MSE) and the structural similarity index(SSIM)[11] with empirical weights shown in equation (3).”
MethodComparing Samsung and Apple Top-End Mobile Cameras by Using NR-IQA Metrics
de Oliveira, A. V. C., Tamayo, S. C., & Cunha, R. N. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-49215-0_35
No-Reference Image Sharpness Assessment Based on Perceptually-Weighted Image Gradients
Andrade, J. (2023) · International Conference on Information, Intelligence, Systems & Applications (IISA) · doi:10.1109/iisa59645.2023.10345886
“Full-reference image quality assessment (FR-IQA) methods [2], [3], [4], [5], [6], [7], [8], [9] provide the best objective results; however, the need of the ground truth pristine image makes this approach unsuitable in most practical applications.”
BackgroundMethodUddin, A. F. M. S., Kim, D., Monira, M. S., Choi, J. W., Chung, T., & Bae, S. (2023) · Journal of Broadcast Engineering · doi:10.5909/jbe.2023.28.6.753
Machine Learning-Based Downscaling of Urban Air Temperature Using Lidar DataPreprint
Chajaei, F., & Bagheri, H. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4671922
Data-Driven Parameterization for A Subgrid-Scale Model: Methods for Improving Model EfficiencyPreprint
Zhu, X., Zhu, X., & Shi, X. (2023) · doi:10.22541/essoar.170365221.12193922/v1
Human Eye Aberrometry Data Generation Using Generative Adversarial Neural Network
Yaroshenko, M. O. (2023) · Microsystems Electronics and Acoustics · doi:10.20535/2523-4455.mea.286366 · Cited by 1
Khalifa, A. S. (2023) · International Conference on Information Science and Technology · doi:10.1109/icist59754.2023.10367058
“The learning process utilized a gain function to maximize two image quality metrics, namely the Structured Similarity Index Measure ( SSIM ) [27] and the Peak-to-Signal Ratio ( PSNR ).”
BackgroundMethodShift-Insensitive Perceptual Feature Based on Quadratic Sum of Gradient Magnitude and Log SignalsPreprint
Chen, C., & Mou, X. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4705652
Zheng, P., Du, W., Zhou, P., Peng, C., Kang, Z., Kong, D., Cheng, S., & Wang, L. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4706046
Gänz, P., Yang, G., Clark, C., Kieß, S., Pienkny, T., Balles, A., Hölzing, A., Facility, E. S. R., Tafforeau, P., & Simon, S. (2024) · e-Journal of Nondestructive Testing · doi:10.58286/29262 · Cited by 2
Wen, C.-M., & Ierapetritou, M. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4711290
Visible and NIR Image Fusion Algorithm Based on Information Complementarity
Li, Z., & Li, B. H. (2024) · Lecture notes in computer science · doi:10.1007/978-981-99-8850-1_33
A Vehicle Detection Method under Strong Infrared Radiation Interference
Zhang, Y. L., Chen, Z., Wang, L., et al. (2023) · International Conference on Video and Image Processing (ICVIP) · doi:10.1145/3639390.3639397
“…includes Mean Square Error (MSE), Mean Absolute Error (MAE), Structural Similarity Index Measurement (SSIM) [27], Multi-Scale SSIM (MS-SSIM) [28], Peak Signal-to-Noise Ratio (PSNR), Universal Image Quality Index (UIQI) [29], Visual Imformation Fidelity (VIF) [30], Information Fidelity…”
BackgroundA Regional Brightness Control Method for a Beam Projector to Avoid Human Glare
Jeon, H.-G., & Lee, K.-H. (2024) · Applied Sciences · doi:10.3390/app14041335
Rottmayer, N., Redenbach, C., & Fahrbach, F. O. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.02.02.578531
A Document Image Moiré Pattern Reduction Method Based on Convolutional Neural Networks
Liu, L., Cao, J., & Luo, X. (2023) · International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · doi:10.1109/icicml60161.2023.10424784
“M indicates the reduction of width and height by a factor, consistent with Reference[6], and in this paper, β”
ResultTraditional Transformation Theory Guided Model for Learned Image Compression
Li, Z., Ge, C., & Li, S. (2024) · International Conference on Consumer Electronics · doi:10.1109/icce59016.2024.10444483
“…trade-off, we regularize the training of the proposed method as: where d ( x, ˆ x ) represents the distortion between the input image and the reconstructed image, with d ( · ) referring to mean square error (MSE) or 1 − MS-SSIM [32]. λ is a hyper-parameter controlling the rate-distortion trade-off.”
MethodDynamic Range Compression of Infrared Images Based on Histogram Equalization with Edge Inversion
Rudikov, S. I., Tsviatkou, V. Y., & Shkadarevich, A. P. (2024) · Doklady BGUIR · doi:10.35596/1729-7648-2024-22-1-108-115
A Literature Survey on Completely Blind Image Quality Evaluator Feature-Enriched
Gavaeikar, D., & Singhai, D. (2023) · International Journal of Scientific Research in Science and Technology · doi:10.32628/ijsrst52310686
A Result Analysis of Feature-Enriched Completely Blind Image Quality Evaluator
Gavaeikar, D., & Singhai, D. (2024) · International Journal of Scientific Research in Science and Technology · doi:10.32628/ijsrst52411119
A Literature Survey on Completely Blind Image Quality Evaluator Feature-Enriched
Gavaeikar, D., & Singhai, D. (2024) · International Journal of Scientific Research in Science and Technology · doi:10.32628/ijsrst52310626
Inpainting of detector saturation artifacts in OCT with deep learning
Nienhaus, J., Matten, P., Schlegl, T., et al. (2024) · doi:10.1117/12.3005432
“Yet, the improvement is reflected also in SSIM and MS-SSIM.”
MethodInfluentialAdversarial Complementary Learning for Just Noticeable Difference Estimation
Yu, D., Jin, J., Meng, L., et al. (2024) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2024.02.009
Combining Deep Learning and Feature Engineering for No-Reference Video Quality Assessment
Decker, A. D., Cock, J. D., & Wallendael, G. V. (2024) · Mile-High Video Conference (MHV) · doi:10.1145/3638036.3640287
Region-Adaptive Video Sharpening Via Rate-Perception Optimization
Pang, Y., Zhao, S., Guo, M., Li, J., & Zhang, L. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446929
Saliency Detection Method of Interfering Objects in Panoramic Images
Zhang, H., & Li, D. (2023) · International Conference on Applied Machine Learning (ICAML) · doi:10.1109/icaml60083.2023.00077
Griffié, J., Zhang, C., Dénéréaz, J., Pham, T.-A., Weissbart, G., Sieben, C., Lambert, A., Veening, J., & Manley, S. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.03.13.584804
Angle Range and Identity Similarity Enhanced Gaze and Head Redirection based on Synthetic data
Qin, J., & Wang, X. (2023) · IEEE International Symposium on Multimedia (ISM) · doi:10.1109/ism59092.2023.00019
“Besides, since the augmentation data contains relatively more noise such as reconstruction artifacts and random background, we use a mixed loss of MS-SSIM [24] and ℓ 1 loss to avoid over-focusing on the pixel difference inspired from [25], [26].”
MethodA Conditional Generative Model for End-to-End Stress Field Prediction of Composite Bolted JointsPreprint
Liu, Y., Lin, Q., Pan, W., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4762283
Li, N., Yang, X., Chen, T., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4768866
Scalable Video Transformer for Full-Frame Video PredictionPreprint
Li, Z., & Liu, F. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4768714
Efficient Low Resolution Image Compression: A Learnable Downscaling Image Compression TechniquePreprint
GILDAS, N. P., Betchewe, G., Kamgang, V. B., Pascal, N. E., Perrin, L. L. M., & Otele, C. G. A. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4768723
Face Inpainting Based on Gan Multi-Dimensional Consistency GuidancePreprint
Li, Y., Zhan, X., Li, H., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4768862
Zhao, H., Sun, C., Shi, D., Hou, J. J., Hou, L., Ni, B., Xu, B., Liu, X., & Xiong, J. (2024) · Optics & Laser Technology · doi:10.1016/j.optlastec.2024.110863
“We employed the Pearson correlation coefficient (PCC) [42] to conduct a comprehensive assessment of the reconstruction performance across the three methods.”
Efficient Low Resolution Image Compression: A Learnable Downscaling Image Compression TechniquePreprint
GILDAS, N. P., Betchewe, G., Kamgang, V. B., Pascal, N. E., Perrin, L. L. M., & Otele, C. G. A. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4772635
Efficient Low Resolution Image Compression: A Learnable Downscaling Image Compression TechniquePreprint
GILDAS, N. P., Betchewe, G., Kamgang, V. B., Pascal, N. E., Perrin, L. L. M., & Otele, C. G. A. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4772692
Applying, evaluating, and accelerating clustering
Thompson, G. (2021) · doi:10.31274/td-20240329-82
Hadžić, I., Pai, S., Taasti, V. T., et al. (2024) · SPIE Medical Imaging: Image Processing · doi:10.1117/12.3007031
Structure Guided Global and Local Attention Transformer for Ship Image InpaintingPreprint
Baek, W., Kang, S., & Yang, Y.-H. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4789301
Silva, A., Moskvyak, O., Long, A., et al. (2024) · IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv57701.2024.00786
Data-Centric Debugging: mitigating model failures via targeted image retrieval
Singla, S., Chegini, A. M., Moayeri, M., & Feizi, S. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00014 · Cited by 4
“Given two images x , z , we use the squared l 2 distance ( ∥ Φ( x ) − Φ( z ) ∥ 2 ) in this space as the visual similarity distance to discover similar images [10,22,57,59,74,76,77,89,90].”
MethodVideo Compression Method Using Vector Quantization
Gotoh, Y., Ohashi, T., & Adhinugraha, K. M. (2024) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-031-57840-3_40
Efficient Low Resolution Image Compression: A Learnable Downscaling Image Compression TechniquePreprint
GILDAS, N. P., Betchewe, G., Kamgang, V. B., Pascal, N. E., Perrin, L. L. M., & Otele, C. G. A. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4798866
Structure Guided Global and Local Attention Transformer for Ship Image InpaintingPreprint
Baek, W., Yang, Y.-H., & Kang, S. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4805585
Murtaza, A., Khairuddin, U. B., Fauzi, A. ‘. M., et al. (2024) · Journal of Advanced Research in Applied Sciences and Engineering Technology · doi:10.37934/araset.44.1.1221
No-Reference Image Sharpness Assessment via Multi-scale Texture Naturalness
Sun, Z., Hua, G., & Xu, Y. (2023) · IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA) · doi:10.1109/aeeca59734.2023.00165
“Further details about the extraction of GLCM features can be found in [13].”
BackgroundMethodImage Hiding Scheme Based on Dense Residual Network
Chen, L., Liu, J., Dong, W., et al. (2023) · International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI) · doi:10.1109/cei60616.2023.10528090
“…eye to image structural information, in order to make the decrypted image more in line with human visual perception, this article adds structural similarity (SSIM) loss ssim L and multi-scale structural similarity MS-SSIM [31] (multi-scale SSIM) loss to the content loss of secret images msssim L .”
BackgroundPanoramic Image Quality Evaluation Method Based on Multi-Feature Fusion
Wu, X. (2023) · International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI) · doi:10.1109/cei60616.2023.10528128
“…objective image quality evaluation meth-ods are: Peak Signal to Noise Ratio (PSNR), Structural Similarity (SSIM) [1] , Multiscale SSIM (MS-SSIM) [2] , Feature, Similarity Index (FSIM) [3] , Deep Image Structure and Texture Similarity (DISTS) [4] , and Visual Saliency Induced (VSI) [5] , among…”
BackgroundInfluentialBaek, W., Kang, S., & Yang, Y.-H. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4831544
Li, Q., & Fang, Q. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4834851
A Light-Field Video Dataset of Scenes with Moving Objects Captured with a Plenoptic Video Camera
Javidi, K., & Martini, M. G. (2024) · Electronics · doi:10.3390/electronics13112223
Analysis of the impact of SSIM parameterization for SAR to EO translation networks
Weerasinghe, R., Young, E., Shaver, R. J., et al. (2024) · doi:10.1117/12.3013326
Symmetric image compression network with improved normalization attention mechanism
Tai, S., Yeh, C.-M., Lee, Y., et al. (2024) · Journal of Electronic Imaging · doi:10.1117/1.jei.33.3.033028
“The peak signal-to-noise ratio (PSNR) and MS-SSIM are used as evaluation criteria.”
MethodInfluentialPhase Fraction Calculation in Multiphase Steel Microstructures Through Semantic Segmentation
Swain, B. R., Cheoi, K. J., & Ko, J. (2024) · International Conference on Applied System Innovation · doi:10.1109/icasi60819.2024.10547821
Video Enhancement to Reduce Reflection and Darkness Caused by the Sunglasses using Fusion Algorithm
Divya, A. K., K, B. H., & J, U. U. (2024) · International Journal of Engineering and Advanced Technology · doi:10.35940/ijeat.e4495.13050624
Targeted Model Inversion: Distilling style encoded in predictions
Jeong, H., Chung, K., Hwang, S. J., & Son, S. (2024) · Computers & Security · doi:10.1016/j.cose.2024.103967
Detection of Stealthy Bitstreams in Cloud FPGAs using Graph Convolutional Networks*
Chaudhuri, J., & Chakrabarty, K. (2024) · IEEE European Test Symposium (ETS) · doi:10.1109/ets61313.2024.10567821
“For an image pair ( Im i , Im j ) , 1 ≤ i, j ≤ ψ, i ̸ = j , the SSIM value [24] is calculated as: , where µ Im i ( µ Im j ) indicates the mean pixel value of Im i ( Im j ) , σ 2 Im i ( σ 2 Im j ) is the variance of Im i ( Im j ) , σ Im i ,Im j is the covariance of the image pair, and l is the range…”
BackgroundVideo Enhancement to Reduce Reflection and Darkness Caused by the Sunglasses using Fusion AlgorithmPreprint
Divya, A. K., Bhagya, H. K., & Ujwal, U. J. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4870100
Tzung-Yuan, L., Yu-Hsing, C., Yao-Ming, L., et al. (2024) · SID Symposium Digest of Technical Papers · doi:10.1002/sdtp.17153
“Finally, our research evaluates the reconstructed image quality at the receiver end using the Multi-Scale Structural Similarity Index Measure (MSSSIM) [17], comparing it with images processed through barrel distortion but not yet through MZMR.”
MethodDSA-QoE: Quality of Experience Evaluation for Streaming Video Based on Dual-Stage Attention
Jia, Z., Min, X., & Zhai, G. (2024) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas58744.2024.10558538
“The signal fidelity-based methods include the full reference MS-SSIM [10] and VMAF [35], the reduced reference STRRED [20] and the no reference NIQE [11].”
MethodFS-BAND: A Frequency-Sensitive Banding Detector
Chen, Z., Sun, W., Zhang, Z., Huang, R., Lu, F., Min, X., Zhai, G., & Zhang, W. (2024) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas58744.2024.10558429
“Concretely, we select 5 full-reference (FR) IQA methods: PSNR, SSIM [13], MS-SSIM [26], LPIPS [27], VMAF BA [28] and 9 no-reference (NR) IQA methods including BRISQUE [16], NIQE [17], NIMA [29], DBCNN [1], HyperIQA [30], StairIQA [31], BBAND [11], CAMBI [12], and DBI [19] as baselines.”
MethodImage Editing Model Based on Multi-Model Feature Fusion
杜, 佳. (2024) · Computer Science and Application · doi:10.12677/csa.2024.146153
Perceptual Image Encryption: A Communication Perspective
Ahmad, I., & Shin, S. (2024) · International Conference on Information Networking · doi:10.1109/icoin59985.2024.10572206
“In our analysis, the image quality was compared using peak signal-to-noise ratio (PSNR) and multiscale structural similarity index measure (MS-SSIM) [13].”
MethodMedical Image Classification using a Many to Many Relation, Multilayered Fuzzy Systems and AI
Akula, K. K., Marcucci, M., Jouffroy, R., et al. (2024) · WSEAS Transactions on Computers archive · doi:10.37394/23205.2024.23.16
CHINGHIZ AITMATOV’S WORKS PUBLICATION DURING THE INDEPENDENCE YEARS
Mehraliyeva, N. M. N. (2024) · PIRETC-Proceeding of The International Research Education & Training Centre · doi:10.36962/piretc31022024-26
Low-Light Image Enhancement with Multimodal Retinex and Depth-Fused RefinementPreprint
Wang, Z., Wu, Y., Li, D., Yin, Z., & Ding, W. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4891109
Self-citationTable image dewarping with key element segmentation
Zhu, Z., Tang, Z., & Gao, L. (2024) · International Journal on Document Analysis and Recognition (IJDAR) · doi:10.1007/s10032-024-00480-z
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.