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 5,301–5,400 of 6,047
Bi, Z., Wu, X., Li, Z., et al. (2022) · doi:10.5194/gmd-2022-117-cec1
Full-Reference Calibration-Free Image Quality AssessmentPreprint
Giannitrapani, P. (2022) · doi:10.36227/techrxiv.19809595
SENetCount: An Optimized Encoder‐Decoder Architecture with Squeeze‐and‐Excitation for Crowd Counting
Meng, X. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/2964683
“To overcome these issues, we apply the structural similarity (SSIM) index [29] or multiscale structural similarity (MS-SSIM) index [30] combined with Euclidean loss.”
MethodAttention-guided Multiple Receptive Field Residual Block for Single Low-light Image Enhancement
Xu, W., Wan, H., & Li, X. (2022) · International Conference on Machine Learning and Computing (ICMLC) · doi:10.1145/3529836.3529909
“For the FENet, we use the Multi-Scale Structural SIMilarity (MS-SSIM) [24] as the main component of the loss function, and further enhance the detailed texture information in the image through ℓ 1 and Total Variation (TV) [1], that is where , and ∇ h (∇ v ) denotes the gradient operator along the horizontal direction.”
MethodWu, X. (2022) · doi:10.5194/gmd-2022-117-ac3
Wu, X. (2022) · doi:10.5194/gmd-2022-117-ac1
Rudikov, S. I., Tsviatkou, V. Y., & Shkadarevich, A. P. (2022) · Informatics · doi:10.37661/1816-0301-2022-19-2-7-25
Wang, Y., Wang, L., Feng, M., et al. (2022) · doi:10.1109/dslw53931.2022.9820183
Self-citationDeep Learning for Image/Video Restoration and Super-resolution
Tekalp, A. M. (2022) · doi:10.1561/9781680839739
DeepSR: A Deep Learning Tool for Image Super ResolutionPreprint
Temiz, H. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4133132
Color distortion and edge feature for perceptual quality assessment
Zeggari, A., Seghir, Z. A., Hemam, M., et al. (2022) · Informatica · doi:10.31449/inf.v46i6.3953
Optimized Video Compression with Residual Split Attention and Swin-Block Artifact ContractionPreprint
Jeny, A. A., & Islam, M. B. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4186554
Efid: Edge-Focused Image Denoising Using a Convolutional Neural NetworkPreprint
Holla, K. S., Park, N., & Lee, B. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4189339
Focused Feature Differentiation Network for Image Quality Assessment
He, G., Wang, Y., Xu, L., Zhang, W., Sun, M., & Wen, X. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00195
“For FR-IQA, many classic methods, such as MSE [9], SSIM [9] and MS-SSIM [10], are widely used in many fields.”
MethodWu, X. (2022) · doi:10.5194/gmd-2022-117-ac2
Novel no-reference multi-dimensional perceptual similarity metric
Rajamani, S. T., Rajamani, K. T., Rani, P., et al. (2022) · Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society · doi:10.1109/embc48229.2022.9871571
“The current approaches for assessing image quality like SSIM [1], MSSIM[2], FSIM[3], or HDR-VDP [4], and the most recent deep learning based approach, perceptual metric [12], are insufficient for determining the quality of images in the context of live acquisition of images where the quality would be continuously chan…”
MethodRang, X., Ma, C., Zheng, Q., et al. (2022) · IEEE Access · doi:10.1109/access.2022.3205013
Automatic Testing and Validation of Level of Detail Reductions Through Supervised Learning
Tamm, M., Shamon, O., Leon, H. A., Tollmar, K., & Gisslén, L. (2022) · IEEE Conference on Games (CoG) · doi:10.1109/cog51982.2022.9893682 · Cited by 2
Walk Like Me: Video to Video Action TransferPreprint
Ghafoor, M., Javed, K., & Mahmood, A. (2022) · doi:10.36227/techrxiv.21070066.v1
Tianrungroj, Y., & Iba, H. (2022) · International Congress on Advanced Applied Informatics (IIAI-AAI) · doi:10.1109/iiaiaai55812.2022.00087
“The mixed loss function Lmix of an image I compared to its ground truth G, was defined as a combination of MSE and multi-scale structural similarity (MS-SSIM) [7] as follows.”
MethodInfluentialPerceptually motivated deep neural network for video compression artifact removal
Ramsook, D., Kokaram, A. C., Birkbeck, N., Su, Y., & Adsumilli, B. (2022) · SPIE Applications of Digital Image Processing · doi:10.1117/12.2633552
Supervised Learning for Makeup Style Transfer
Strawa, N., & Sarwas, G. (2022) · Computer Science Research Notes · doi:10.24132/csrn.3201.25
Advances in Image and Video Quality Assessment
Seshadrinathan, K., & Bovik, A. C. (2008) · Springer eBooks · doi:10.1007/978-0-387-78414-4_6 · Cited by 1
Self-citationEfid: Edge-Focused Image Denoising Using a Convolutional Neural NetworkPreprint
Holla, K. S., Park, N., & Lee, B. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4185499
Range Image Quality Assessment by Structural Similarity
(2012) · SpringerReference · doi:10.1007/springerreference_72923
Wang, Z., & Lai, L. (2022) · International Conference on Digital Image Processing · doi:10.1117/12.2643807
Self-citationContrast Quality Measure: Full-Reference Image Quality Assessment Metric for Infrared Images
Stojanović, N., Bondžulić, B. P., Pavlović, B., & Ristić, V. (2022) · New Trends in Signal Processing (NTSP) · doi:10.23919/ntsp54843.2022.9920403
Lu, Y., Guo, Y., Huang, Y., et al. (2022) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc55140.2022.9921977
“Therefore, for the output value and the true value at any pixel P , L ms can be expressed as More detailed introduction to MS-SSIM can be found in [30].”
BackgroundUhl, T., Hoppe, C., & Klink, J. H. (2022) · International Conference on Software, Telecommunications and Computer Networks (SoftCOM) · doi:10.23919/softcom55329.2022.9911530
Retina-Inspired Spatio-Temporal Filtering for Dynamic Video Coding
Doutsi, E., Antonini, M., & Tsakalides, P. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897355
Direct Handheld Burst Imaging to Simulated Defocus
Wu, M.-L., Dayana, V. R. K., & Hwang, H. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897610
“where Lssim(x, y) is negative multiscale structural similarity [21] with two scales weighted [0.”
BackgroundLow-Complexity Scaler Based on Convolutional Neural Networks for Adaptive Video Streaming
Kim, J., Kim, D., Park, M. W., et al. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897395
“The performance is evaluated using BD-rates [14] based on Peak Signal-to-Noise Ratio (PSNR), Multi-Scale Structural Similarity Index Metric (MS-SSIM) [15] and Video Multi-method Assessment Fusion (VMAF) [16].”
MethodInfluentialDhaneshwar, R., Kaur, M., & Kaur, M. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-19-5224-1_22
Applied Single Image Super-Resolution for Aerial Imagery Enhancement
Marathe, A., Takalikar, M. S., & Bhowmick, T. (2022) · IEEE Global Conference on Computing, Power and Communication Technologies (GlobConPT) · doi:10.1109/globconpt57482.2022.9938277
“The works found enhanced resolution, better performance for object detection and among the CNN architectures which were tested using PSNR and SSIM [41], [43], it was found that PSNR and SSIM the deeper, residual networks delivered the best results.”
MethodAn Image Resizing Function Embedded in an Inverse Discrete Cosine Transform
Sinchai, A., & Tuwanut, P. (2022) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc55196.2022.9952480
Ivanov, A., Pavlov, V. A., & Minh, N. C. (2022) · International Conference on Electrical Engineering and Photonics (EExPolytech) · doi:10.1109/eexpolytech56308.2022.9950964
SUPER RESOLUÇÃO DE IMAGENS SÍSMICAS
PINTO, P. F. A. (2022) · doi:10.17771/pucrio.acad.61491
Katsavounidis, I. X., Robitza, W., Puri, R., et al. (2021) · ACM SIGMultimedia Records · doi:10.1145/3577934.3577939
Quality Assessment of Light-Field Image
Gu, K., Liu, H., & Zhou, C. (2022) · Advances in computer vision and pattern recognition · doi:10.1007/978-981-19-3347-9_6
Quality Assessment of 3D-Synthesized Images
Gu, K., Liu, H., & Zhou, C. (2022) · Advances in computer vision and pattern recognition · doi:10.1007/978-981-19-3347-9_3
Multi-scale Coarse-to-Fine Network for Demoiréing
Liu, C., Li, J., Gang, R., Feng, S., & Chang, M. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-18916-6_19
Quality Assessment of Virtual Reality Images
Gu, K., Liu, H., & Zhou, C. (2022) · Advances in computer vision and pattern recognition · doi:10.1007/978-981-19-3347-9_7
Gul, M. S. K., Suleman, H., Bätz, M., et al. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956352
“Additionally, the proposed method outperforms all tested image codecs on MS-SSIM, a perceptual metric capturing the structural quality of an image.”
MethodInfluential2-D latent space models: Layer-wise perceptual training and spatial grounding
Grujicic, D., & Blaschko, M. B. (2022) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr56361.2022.9956349
“Due to the standardized nature of the CelebA dataset, we do not consider the multi-scale variant of SSIM (MS-SSIM).”
BackgroundA Novel Video Quality Evaluation Method Based on Coarse-to-fine Strategy in Traffic Scenario
Wang, H., Chen, H., Tu, H., et al. (2022) · doi:10.1109/mlccim55934.2022.00048
“Later, Wang et al. [11] proposed a Structural Similarity (SSIM) measurement algorithm, which improved the performance of the algorithm, but the complexity was high.”
BackgroundChen, J. (2022) · Academic Journal of Engineering and Technology Science · doi:10.25236/ajets.2022.051209
Image Quality Assessment for Wood Images
Rajagopal, H., Mokhtar, N. B., & Khairuddin, A. S. M. (2022) · IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET) · doi:10.1109/iicaiet55139.2022.9936864
“The explanation of these metrics is shown in Table I. Higher MSSIM, SSIM, FSIM and IWSSIM scores and lower GMSD scores are produced for higher quality images.”
BackgroundMethodInfluentialStegIm: Image in Image Steganography
Tasevski, I., Dobreva, J., Andonov, S., et al. (2022) · Communications in computer and information science · doi:10.1007/978-3-031-22792-9_2
On Pre-chewing Compression Degradation for Learned Video Compression
Ho, M. M., Sun, H., Zhang, Z., et al. (2022) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip56404.2022.10008873
“THE COMBINATION OF L1 AND LPIPS PROVIDES THE BEST PERFORMANCE IN PSNR↑, LPIPS↓, AND MS-SSIM↑ [16] ON AVERAGE AS BOLD.”
BackgroundDual-Domain Diffusion based Progressive Style Rendering Towards Semantic Structure PreservationPreprint
Tao, M., & Jiang, R. (2023) · doi:10.36227/techrxiv.21880650
Dual-Domain Diffusion based Progressive Style Rendering Towards Semantic Structure PreservationPreprint
Tao, M., & Jiang, R. (2023) · doi:10.36227/techrxiv.21880650.v1
RETRACTED: Simulating human visual perception behaviors for video quality assessment
Sheng, Y., Zhang, L., & Li, Y. (2023) · Journal of Electronic Imaging · doi:10.1117/1.jei.32.6.062508
RetractedExploring Learning with Deep Heterogeneous Descriptor-based Sampling
Wang, C., Ke, W., Wu, Z., & Xiong, Z. (2022) · IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS) · doi:10.1109/ccis57298.2022.10016342
Learned Image Compression with Inception Residual Blocks and Multi-Scale Attention Module
Fu, H., Liang, F., Liang, J., et al. (2022) · Picture Coding Symposium · doi:10.1109/pcs56426.2022.10018002
“For MS-SSIM, the parameter λ is set to 12, 40, 80 and 120.”
BackgroundInfluentialHuman Imperceptible Attacks and Applications to Improve Fairness
Hua, X., Xu, H., Blanchet, J., & Nguyen, V. A. (2022) · Winter Simulation Conference · doi:10.1109/wsc57314.2022.10015376 · Cited by 3
“Traditional IQA methods include SSIM [62], MS-SSIM [63] FSIM [73], and PSNR [37].”
MethodNew Quality Metric for Compressed Images
Abdulsattar, F. S., Mahammad, M., & Zaghar, D. R. (2020) · Anbar journal for engineering sciences/Mağallaẗ al-anbār li-l-ʻulūm al-handasiyyaẗ · doi:10.37649/aengs.2023.176830
A Bokeh Image Generation Technique using Machine Learning
Huang, H., Ito, Y., & Nakano, K. (2022) · International Symposium on Computing and Networking · doi:10.1109/candar57322.2022.00020
“SSIM is to evaluate images in terms of brightness, contrast, and structure, with larger values indicating better output image quality.”
MethodThe Way to picture Reality: A Review, Evaluation and Recipe of Image HarmonizationPreprint
Tian, Y., Hou, J., & Zhang, Y. (2023) · Research Square · doi:10.21203/rs.3.rs-2624331/v1
Effect of the salt mist testing on imaging resolution of the optical imaging system
Wang, T., Chen, S., & Pang, Y. (2023) · International Conference on Precision Instruments and Optical Engineering (PIOE) · doi:10.1117/12.2667355
Influence of damp heat testing on color revent characteristics of optical imaging system
Wang, T. (2023) · International Conference on Optoelectronic Materials and Devices (ICOMD) · doi:10.1117/12.2674010
Deep Photographic Steganography for Display-to-Camera Communication
Yang, Q., & Mao, Y. (2022) · China Automation Congress (CAC) · doi:10.1109/cac57257.2022.10055088
Zabihi, J., & Grailu, H. (2023) · Journal of Information Systems and Informatics · doi:10.51519/journalisi.v5i1.423
Attention-guided multi-scale illumination estimation for low-light image enhancement
Baoxiang, T., Du, H., & Tan, Y. (2022) · doi:10.1109/icftic57696.2022.10075183
“In addition, for constraining the effect of image restoration in the local dimension, MS-SSIM (multi-scale structural similarity) [11] loss function is adapted to optimize the model.”
MethodOmnidirectional Image Quality Assessment With a Superpixel-Based Sparse Model
Wan, Z., Yan, X., Yang, Q., et al. (2022) · International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) · doi:10.1109/ispacs57703.2022.10082801
Said, S., Clauser, P., Ruiter, N. V., et al. (2023) · SPIE Medical Imaging: Image-Guided Procedures, Robotic Interventions, and Modeling · doi:10.1117/12.2653978
“SSIM is responsible for extracting three features; luminance, image contrast, and structure while MS-SSIM supports more variations such as image resolution.(7) The second method is bias, difference in variance (DIV), and standard deviation difference (SDD).”
Method3D point cloud quality assessment method using Mahalanobis distance
Laazoufi, A., Hassouni, M. E., & Cherifi, H. (2022) · International Conference on Signal-Image Technology & Internet-Based Systems (SITIS) · doi:10.1109/sitis57111.2022.00097
“[23] 0.3654 0.2789 2.2440 SSIM-MS [30] 0.3659 0.2592 2.2437 SSIM-IW [31] 0.4339 0.3285 2.1720 FSIM-IQA [32] 0.3196 0.3019 2.2843 VIF-IQA [33] 0.5243 0.5647 2.0653 3D-to-2D-PCQA [25] 0.6076 0.6020 1.8635 Model-based P-to-point [15] 0.0466 0.7009 2.4081 P-to-plane [15] 0.0462 0.6881 2.4080 PCQM [20]…”
InfluentialGÜÇLENDİRİLMİŞ GRADYAN MİNİMİZASYONU KULLANARAK MEDİKAL GÖRÜNTÜLERDE GÜRÜLTÜ ARINDIRMA
Ertaş, M. (2023) · Uludağ University Journal of The Faculty of Engineering · doi:10.17482/uumfd.1139249
CID22: Large-Scale Subjective Quality Assessment for High Fidelity Image CompressionPreprint
Sneyers, J., Baruch, E. B., & Vaxman, Y. (2023) · doi:10.36227/techrxiv.22659061 · Cited by 1
Hierarchical Existential Prior Based on Expanded Pseudo Label for Crack DetectionPreprint
Fang, J. (2023) · Research Square · doi:10.21203/rs.3.rs-2870838/v1
Optimizing Macroblock Tree Algorithm for Real-Time Video Encoding in HW
Johar, S., Bansal, V. K., & Shukla, M. N. (2023) · International Conference on Signal Processing and Integrated Networks (SPIN) · doi:10.1109/spin57001.2023.10116456
Dual-stream encoded fusion saliency detection based on RGB and grayscale images
Xu, T., Zhao, W., Chai, H., & Cai, L. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-15217-z
“…a weighted mixing loss function is designed in this paper, which is defined as: L = w bce l bce + w ssim l ssim (11) Where l bce and l ssim are BCE [2] loss functions and SSIM [40] loss functions respectively. w bce and w ssim are weights of BCE loss function and SSIM loss function respectively.”
BackgroundADAPTIVE ILLUMINATION CORRECTION ALGORITHM BASED ON RETINEX TECHNOLOGY FOR CAMERA TRAP IMAGES
Зотин, А. Г., & Проскурин, А. В. (2023) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xlviii-2-w3-2023-275-2023
Mostofa, M. (2023) · The Research Repository @ WVU (West Virginia University) · doi:10.33915/etd.11758
Color-aware Deep Temporal Backdrop Duplex Matting System
Hachmann, H., & Rosenhahn, B. (2023) · ACM Multimedia Systems Conference (MMSys) · doi:10.1145/3587819.3590973
“For quantitative evaluation, the matting results are composited with checkerboard backgrounds, compared to the ground truth, and evaluated with the following metrics: PSNR, MS-SSIM [50] and the perceptual Video Multi-Method Assessment Fusion (VMAF) [26].”
MethodInfluentialCompressive sensing-based tomography for Absolute X-ray UltraViolet (AXUV) diagnostics
Yang, M., Cheng, Z., Wang, S., et al. (2023) · Review of Scientific Instruments · doi:10.1063/5.0147418
AI-BASED LIGHT PARALLEL VIDEO ENCODER
Tarchouli, M., Rivière, M., Guionnet, T., et al. (2023) · Mile-High Video Conference (MHV) · doi:10.1145/3588444.3591008
“Square Error (MSE) orMulti-Scale Structural Similarity Index (MS-SSIM)[29].”
BackgroundMethodMultiobjective Image Compression based on Tensor Decomposition
Cao, B., Yang, X., Li, Z., et al. (2023) · International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) · doi:10.1109/icccbda56900.2023.10154835
“The multi-scale SSIM(MS-SSIM) method [5] is based on the SSIM.”
MethodMaruthi, R., Anusha, P., Sankar, P., & Thiyagaragan, K. (2023) · International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT) · doi:10.1109/iceeict56924.2023.10157402
“(vi) Multi Scale- Structural Similarity Index (MS-SSIM) The MS-SSIM approach is a substantial improvement over SSIM since it offers greater versatility than single scale methods [16].”
MethodArtificial intelligence applications in oncology to augment data and support decisions
Wang, Z. (2023) · Research Publications (Maastricht University) · doi:10.26481/dis.20230711zw
Self-citationVideo Compression using Neural Weight Step and Huffman Coding Techniques
Al-Sudani, F. A. J. (2023) · Journal of University of Babylon for Pure and Applied Sciences · doi:10.29196/jubpas.v31i2.4656
Image Frequency Separation Residual Network for End-to-end RAW to RGB Mapping
Dong, M., Zhou, W., Pang, C., Zhang, X., & Lou, X. (2023) · IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) · doi:10.1109/aicas57966.2023.10168597
“Due to the large amount of image information in the low-frequency part, we use a mixed loss function as follows: where L V GG denotes the VGG [30]-based perceptual loss, L SSIM denotes the SSIM Loss [31] and L L 1 is the L1 loss.”
MethodDevelopment of Image Quality Assessment (IQA) For Haze Prediction
Rajagopal, H., Sudheer, S., Jothi, N., et al. (2023) · Proceedings of International Conference on Artificial Life and Robotics · doi:10.5954/icarob.2023.os1-2
ViT with diamond patches for lane line detection under occlusionPreprint
Shi, X., Wang, R., Zhang, H., Li, Z., Su, Y., Ti, Y., & Song, T. (2023) · Research Square · doi:10.21203/rs.3.rs-3179683/v1
Zhang, X., Yu, Y., Wang, Y., Chen, X., & Wang, C. (2023) · Sensors · doi:10.3390/s23146562
“BASNet [20] employs a hybrid loss that incorporates SSIM [48] to capture the structural information in an image.”
MethodConditional Diffusion Models for Semantic 3D Medical Image SynthesisPreprint
Dorjsembe, Z., Pao, H.-K., Odonchimed, S., & Xiao, F. (2023) · doi:10.36227/techrxiv.23723787.v1 · Cited by 12
Disent-Eg3d: Disentangled Identity Control on 3d Generator Without 3d DataPreprint
Huang, J., Yu, H., & Zhang, J. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4520888
Interpretable Image/Video Compression by Extracting the Least Context Map
Huang, H., & Yang, W. (2023) · International Conference on Computing, Networks and Internet of Things (CNIOT) · doi:10.1145/3603781.3603841
“from those LCMs can achieve an average MS-SSIM [23] score higher than 0.”
BackgroundInfluentialSuzuki, S., Okamoto, A., Michibayashi, K., et al. (2023) · International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence (ISMSI) · doi:10.1145/3596947.3596958 · Cited by 1
“We also use a variant of the SSIM index called the multi-scale structural similarity (MS-SSIM) index [20], which evaluates various structural similarities at different image scales, and the features similarity index matrix (FSIM) index [21], [22], which evaluates an image quality based on the fact that the human visua…”
MethodNeyigapula, B. S. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4528609
MedSteGAN: Medical Embedding-Optimized Steganography with Improved GANPreprint
Peng, Y., Fu, C., Zheng, Y., et al. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4533667
Neyigapula, B. S. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4535851
Neyigapula, B. S. (2023) · Research Square · doi:10.21203/rs.3.rs-3240498/v1
Practical volumetric speckle reduction in OCT using deep learning
Chintada, B. R., Ruiz-Lopera, S., Restrepo, R., et al. (2023) · doi:10.1117/12.2670781
“We quantified the similarity between the ground truth and our network produced tomograms using the structural similarity index measure (SSIM) [4] and multiscale SSIM (MS-SSIM) [5]; for this example, their values were 0.”
MethodInfluentialScene text image correction based on transformer
Jin, M., Tu, X., Han, J., & Chen, C. (2023) · International Conference on Electronic Information Technology (EIT) · doi:10.1117/12.2685812
“As shown in Table 1, our models outperformed several popular models, Proc. of SPIE Vol. 12719 127191Q-6 especially the state-of-the-art DewarpNet[6] model, with a 9.22% decrease in MS-SSIM evaluation metric and a 2.50% increase in LD evaluation metric.”
MethodInfluentialPredicting dark-field images of H and E-stained esophageal specimens
Arli, B., Dinç, Ö. F., Turker-Burhan, M., et al. (2023) · doi:10.1117/12.2672202
Image Reconstruction Using Cellular Automata and Neural Networks
Loghin, M.-A., & Andreica, A. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-40725-3_54
Yejun, 杨. Y., Gang, 刘. L., Gang, 肖. X., et al. (2023) · Laser & Optoelectronics Progress · doi:10.3788/lop222204
Optimization study of parameters for laser-induced thermal treatment of the esophageal mucosal layer
Turker-Burhan, M., Ersoy, N., Bağrıyanık, A., et al. (2023) · doi:10.1117/12.2671739
Deep Learning-Based Self-Absorption Correction Method for Fan-Beam X-ray Fluorescence CT
Sun, M., Shanghai, J., Hu, X., et al. (2023) · International Conference on Optical Communications and Networks (ICOCN) · doi:10.1109/icocn59242.2023.10236281
“In the training phase, we used the Multi Scale Structural Similarity Index Measure(MS-SSIM) [3] as the loss function, and used the Adam optimizer to minimize the loss function.”
MethodTask-Adaptive Feature Matching Loss for Image Deblurring
Chang, C.-C., Yang, B.-C., Liu, Y., Chen, J.-C., Jhuo, I., & Lin, Y. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10222595
“For image deblur-ring, most existing models adopt objective metrics, which are divided into other two types: full-reference [11, 12, 13, 14, 15, 16, 17, 2, 18, 9, 10] and no-reference metrics [19, 20, 8, 21, 22, 23, 24].”
Method
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.