Multiscale structural similarity for image quality assessment
The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index; none of the 14 sources its claims cite is checked for support yet.
Abstract
The structural similarity image quality paradigm is based on the assumption that the human visual system is highly adapted for extracting structural information from the scene, and therefore a measure of structural similarity can provide a good approximation to perceived image quality. This paper proposes a multiscale structural similarity method, which supplies more flexibility than previous single-scale methods in incorporating the variations of viewing conditions. We develop an image synthesis method to calibrate the parameters that define the relative importance of different scales. Experimental comparisons demonstrate the effectiveness of the proposed method.
Overview
CoChat Summary
TL;DR
This paper proposes a multi-scale structural similarity (MS-SSIM) image quality method that combines contrast and structure comparisons across scales and luminance comparison at the coarsest scale. On the LIVE JPEG/JPEG2000 database, MS-SSIM outperformed PSNR, the Sarnoff model, and single-scale SSIM variants on all reported evaluation criteria.
Key findings
- MS-SSIM achieved the best reported performance: CC 0.969, ROCC 0.966, MAE 3.86, RMS 4.91, and OR 1.16%, compared with the best single-scale SSIM at M=2 (CC 0.963, ROCC 0.959, MAE 4.21, RMS 5.38, OR 2.62%) and PSNR (CC 0.905, ROCC 0.901, MAE 6.53, RMS 8.45, OR 15.7%).
- Single-scale SSIM performance varied with scale; the best single-scale result was at M=2, and single-scale SSIM tended to give higher scores as scale increased.
- The calibrated cross-scale exponents were β1=γ1=0.0448, β2=γ2=0.2856, β3=γ3=0.3001, β4=γ4=0.2363, and α5=β5=γ5=0.1333.
- The authors conclude that multi-scale SSIM provides a meaningful balance between scales and outperforms the best single-scale SSIM and state-of-the-art image quality metrics.
Methods
- The MS-SSIM system iteratively applies a low-pass filter and downsamples by 2; at each scale it computes contrast and structure comparisons, computes luminance comparison only at Scale M, and combines them using exponents normalized so that ∑γj=1.
- Cross-scale parameters were calibrated by image synthesis: 5 scales and 12 distortion levels (range 2^3 to 2^14) were used with 10 original 64×64 images, producing 600 distorted images; 8 subjects selected images of equal perceived quality across scales at a viewing distance of 32 pixels per degree of visual angle.
- Evaluation used the LIVE database with 344 JPEG and JPEG2000 compressed images (bit rate 0.028 to 3.150 bits/pixel), MOS from 13–25 subjective scores, and compared PSNR, Sarnoff JNDmetrix 8.0, single-scale SSIM for M=1–5, and MS-SSIM using CC, MAE, RMS, OR, and ROCC after logistic mapping.
Limitations
- Stated: the image-synthesis calibration approach is “still rather crude,” and the authors are working on a more systematic approach.
- Stated: CSF cannot be directly used to derive the parameters because it is typically measured at visibility threshold with simplified stimuli, whereas the goal is comparing complex structured images at visible distortion levels.
- Evident from the text: calibration used only 10 original 64×64 grayscale images and 8 subjects, including one author, and evaluation was limited to the LIVE JPEG/JPEG2000 database.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
0 Valid · 1 Not valid · 14 Not checked · 18 Own results and interpretations
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It can also be observed that the single-scale model tends to supply higher scores with the increase of scales.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Finally, for every one of the objective evaluation criteria, multi-scale SSIM model outperforms all the other models, including the best single-scale SSIM model, suggesting a meaningful balance between scales.”
- Also stated in: § 5. DISCUSSIONS · p. 4 · hedged
“Experiments show that with an appropriate parameter settings, the multi-scale method outperforms the best single-scale SSIM model as well as state-of-the-art image quality metrics.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 5. DISCUSSIONS · p. 4 · hedged
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In general, the subjects agreed with each other on each image more than they agreed with themselves across different images.”
plainstates an associationn = 8- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The resulting parameters we obtained are β 1 = γ 1 = 0.0448, β 2 = γ 2 = 0.2856, β 3 = γ 3 = 0.3001, β 4 = γ 4 = 0.2363, and α 5 = β 5 = γ 5 = 0.1333, respectively.”
plainn = 8- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“However, the SSIM index algorithm introduced in [5] is a single-scale approach.”
What the sources say
- Not matchedcites [5] [5] Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, 'Image quality assessment: From error measurement to structural similarity,' IEEE Trans. Image Processing , vol. 13, Jan. 2004. -
More than one paper fits this citation.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
10 more claims
Create a free account to see all 33 claims and every source verdict.
- It may state two separate claims as one. 8
- Probably not a substantial claim. 13
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Further, as research in quality assessment has demonstrated, incorporating multiscale information when assessing quality produces QA algorithms that perform better in terms of correlation with human perception [13], [29].”
From No-Reference Image Quality Assessment in the Spatial Domain (2012) · cites this paper as [13]
Citations
Cites
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892
Self-citationA universal image quality index
Wang, Z., & Bovik, A. C. (2002) · IEEE Signal Processing Letters · doi:10.1109/97.995823 · Cited by 5,757
Self-citationImage quality measures and their performance
Eskicioglu, A. M., & Fisher, P. S. (1995) · IEEE Transactions on Communications · doi:10.1109/26.477498 · Cited by 2,117 · cited 1×
“Traditional perceptual image quality assessment methods are based on a bottom-up approach which attempts to simulate the functionality of the relevant early human visual system (HVS) components.”
BackgroundA Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients
Portilla, J., & Simoncelli, E. P. (2000) · International Journal of Computer Vision · doi:10.1023/a:1026553619983 · Cited by 1,806 · cited 2×
“These synthesis methods provide a powerful and efficient means of testing a model, and have the added benefit that the resulting images suggest improvements that might be made to the model [11].”
MethodSelf-citation(1995) · Medical Entomology and Zoology · Cited by 1,212
Pyramid-based texture analysis/synthesis
Heeger, D. J., & Bergen, J. R. (1995) · Proceedings of the 22nd annual conference on Computer graphics and interactive techniques - SIGGRAPH '95 · doi:10.1145/218380.218446 · Cited by 1,095
Video quality assessment based on structural distortion measurement
Wang, Z., Lu, L., & Bovik, A. C. (2004) · Signal Processing: Image Communication · doi:10.1016/s0923-5965(03)00076-6 · Cited by 1,024
Self-citationImage Quality Assessment: From Error Measurement to Structural Similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · Cited by 919
Self-citationTeo, P. C., & Heeger, D. J. (2002) · Proceedings of 1st International Conference on Image Processing · doi:10.1109/icip.1994.413502 · Cited by 471
Objective video quality assessment
(2003) · Handbook of Video Databases · doi:10.1201/9780203489864-45 · Cited by 359
Research works printed but not linked: 2
- 0, JNDmetrix Technology, Sarnoff Corporation
- 2000, Final report from the video quality experts group on the validation of objective models of video quality assessment, VQEG
Cited by
Items 2,001–2,100 of 6,047
One-to-Multiple Clean-Label Image Camouflage (OmClic) based backdoor attack on deep learning
Wang, G., Ma, H., Gao, Y., Abuadbba, A., Zhang, Z., Kang, W., Al-Sarawi, S. F., Zhang, G., & Abbott, D. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.111456 · Cited by 16
BAND-2k: Banding Artifact Noticeable Database for Banding Detection and Quality Assessment
Chen, Z., Sun, W., Jia, J., Lu, F., Zhang, Z., Liu, J., Huang, R., Min, X., & Zhai, G. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3366522 · Cited by 17
“2) Baseline Algorithms: We include a number of representative IQA algorithms in our evaluation as references to be compared against : • General FR IQA methods: We choose PSNR, SSIM [36], MS-SSIM [37], LPIPS [38] as baselines.”
MethodBlurriness-Guided Underwater Salient Object Detection and Data Augmentation
Peng, Y., Lin, Y., Peng, W., & Liu, C.-L. (2024) · IEEE Journal of Oceanic Engineering · doi:10.1109/joe.2023.3344154 · Cited by 19
“…in [14], including the binary cross-entropy loss (cid:2) bce for penalizing pixels classified into wrong classes, Intersection over Union loss [64] (cid:2) iou for punishing the dissimilarity of two sets, and Structural SIMilarity (SSIM) loss [65] for encouraging the compared images’ similarity.”
BackgroundTrade-Offs in Fine-Tuned Diffusion Models between Accuracy and Interpretability
Dombrowski, M., Reynaud, H., Müller, J. P., Baugh, M., & Kainz, B. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i19.30095 · Cited by 24
ZS-SRT: An efficient zero-shot super-resolution training method for Neural Radiance Fields
Feng, X. Z., He, Y., Wang, Y., Wang, C., Kuang, Z., Ding, J., Qin, F., Yu, J., & Fan, J. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127714 · Cited by 22
“We quantitatively evaluate our approach with the following three metrics: Peak Signal Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM) [44], and Learned Perceptual Image Patch Similarity (LPIPS) [45].”
Crowd-Sourced NeRF: Collecting Data From Production Vehicles for 3D Street View Reconstruction
Qin, T., Li, C., Ye, H., Wan, S., Li, M., Liu, H., & Yang, M. Z. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3415394 · Cited by 23
“We reported PSNR, SSIM [37], and LPIPS [38] metrics for novel view rendering.”
MethodPerceptual Depth Quality Assessment of Stereoscopic Omnidirectional Images
Zhou, W., & Wang, Z. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3449696 · Cited by 17
“…to the characteristics of the HVS, the structure similarity (SSIM) [29] and several variants have been proposed, such as multiscale SSIM (MS-SSIM) [30] and feature similarity (FSIM) [31], etc. Intuitively, these 2D IQA metrics can be directly applied to the perceptual quality assessment of OIs by…”
Self-citationRoDLA: Benchmarking the Robustness of Document Layout Analysis Models
Chen, Y., Zhang, J., Peng, K., Zheng, J., Liu, R., Torr, P. H. S., & Stiefelhagen, R. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01473 · Cited by 34
“MS-SSIM (Multi-Scale Structural Similarity Index) [62] evaluates image quality by considering difference in structural information across different resolutions, as: where l M ( x,y ) represents the luminance difference at the M -th scale, and c j ( x,y ) , s j ( x,y ) are the contrast and structure…”
BackgroundMultimodal Low-light Image Enhancement with Depth Information
Wang, Z. R., Li, D., Li, G., Zhang, Z., & Jiang, R. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3680741 · Cited by 31
Self-citationLe, V.-T., Jin, H., & Kim, Y.-G. (2025) · Applied Intelligence · doi:10.1007/s10489-024-06042-4 · Cited by 19
Fan, H., Jin, C., & Li, M. (2025) · Entropy · doi:10.3390/e27030282 · Cited by 14
ViDDAR: Vision Language Model-Based Task-Detrimental Content Detection for Augmented Reality
Xiu, Y., Scargill, T., & Gorlatova, M. A. (2025) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2025.3549147 · Cited by 34
“However, most traditional algorithms [17,36,41,42] developed for FR-IQA rely on local features, such as pixel-or patch-level comparisons, limiting their capability to under-• stand environmental information, especially in complex scenes [2].”
Adaptive high-frequency clipping for improved image quality assessment
Gu, K., Zhai, G., Liu, M., Xu, Q., Yang, X., Zhou, J. W., & Zhang, W. (2013) · Visual Communications and Image Processing · doi:10.1109/vcip.2013.6706347 · Cited by 14
García, M., Felici-Castell, S., & Segura-García, J. (2016) · Network Protocols and Algorithms · doi:10.5296/npa.v8i1.8850 · Cited by 14
“MSSSIM [44] MultiScale SSIM based on SSIM metric of several downscaled levels of original images.”
MethodFree viewpoint video quality assessment based on morphological multiscale metrics
Sandic-Stankovic, D. D., Battisti, F., Kukolj, D., et al. (2016) · International Conference on Quality of Multimedia Experience (QoMEX) · doi:10.1109/qomex.2016.7498949 · Cited by 14
Quality-of-experience prediction for streaming video
Duanmu, Z., Rehman, A., Zeng, K., & Wang, Z. (2016) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2016.7552859 · Cited by 18
“TEST To demonstrate the effectiveness of our framework, four VQA algorithms, namely PSNR, SSIM [10], MSSSIM [11] and SSIMplus [14], are employed as the frame-level video presentation quality measure.”
MethodInfluentialSelf-citationRetina inspired no-reference image quality assessment for blur and noise
Joshi, P., & Prakash, S. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-4418-2 · Cited by 14
“The proposed technique is compared with several other existing FR-IQA and NR-IQA techniques such as PSNR [32], SSIM [32], MS-SSIM [31], BIQI [18], LBIQ [29], CBIQ [36], BLIINDS-II [24], DIIVINE [19], BRISQUE [15], NIQE [17], LQF [16], QAC [35], NRQI [9], TMIQ [16], SA-SS, SA-ZC [37] and BIQES [25] in different experim…”
MethodNo-Reference Quality Assessment of Noise-Distorted Images Based on Frequency Mapping
Yang, G., Liao, Y., Zhang, Q., Li, D., & Yang, W. T. (2017) · IEEE Access · doi:10.1109/access.2017.2764126 · Cited by 14
“Table 2 lists the SROCC values of FMIQA index and other FR- and NR-IQA metrics for noise-distorted images on the LIVE, CSIQ, and TID2013 databases, where PSNR, SSIM [16], GMSD [58], GSSIM [59], MS-SSIM [60], RFSIM [51], and FSIM [61] are classical FR-IQA metrics, BLIINDSII [45], FRIQUEE [46], CORNIA [62], NIQE [63], Q…”
MethodQin, Z., Lin, Y., Lin, F., et al. (2018) · Journal of the Society for Information Display · doi:10.1002/jsid.644 · Cited by 14
Perceptual Image Quality Assessment for Various Viewing Conditions and Display Systems
Chubarau, A., Akhavan, T., Yoo, H., Mantiuk, R., & Clark, J. J. (2020) · Electronic Imaging · doi:10.2352/issn.2470-1173.2020.9.iqsp-067 · Cited by 18
“The underlying content can be compared using various strategies: mean-squared difference (MSE), signal-to-noise ratio (PSNR), structural similarity (SSIM [2], MS-SSIM [3], IW-SSIM [4], TMQI [5]), naturalness statistics and information content (VIF [6, 7]), contrast visibility (HDR-VDP [8, 9]), low-level feature simila…”
BackgroundImage Quality Assessment Using Kernel Sparse Coding
Zhou, Z.-H., Li, J., Quan, Y.-H., & Xu, R.-T. (2021) · IEEE transactions on multimedia · doi:10.1109/tmm.2020.3001472 · Cited by 12
ModeNet: Mode Selection Network for Learned Video Coding
Ladune, T., Philippe, P., Hamidouche, W., Zhang, L., & Olivier Déforges, A. (2020) · Machine learning for signal processing ... · doi:10.1109/mlsp49062.2020.9231841 · Cited by 15
“e-distortion trade-off: L() = D(x^ t;x t) + (R m + R c); (8) where D denotes a distortion metric. Following the CLIC20 P-frame test conditions, the Multi Scale Structural Similarity Metric (MS-SSIM)[15] is used: D(x^ t;x t) = 1 MS-SSIM(^x t;x t): As this work focuses on mode selection, a naive prediction x~ t = ^x t 1…”
MethodSize-Invariant Visual Cryptography With Improved Perceptual Quality for Grayscale Image
Sun, R., Fu, Z., & Yu, B. (2020) · IEEE Access · doi:10.1109/access.2020.3021522 · Cited by 14
“The MSSIM [29], an acknowledged measurement standard, considers the combination of local luminance comparison, the local contrast comparison, and the local correlation of two images as one metric.”
BackgroundA Weighted Mean Absolute Error Metric for Image Quality Assessment
Hao, S., & Li, S.-M. (2020) · Visual Communications and Image Processing · doi:10.1109/vcip49819.2020.9301889 · Cited by 16
“We compared the 13 kinds of state-of-the-art or widely cited FR-IQA algorithms, MAE, PSNR, SSIM [1], MSSIM [2] , VSI [5], VIF [8], PAMSE [11], IWPSNR [3], IWSSIM [3] , ADDSSIM [12], FSIM [7], GMSD [6], SCQI [13], where IWPSNR and P a M s E are based on errors, where FSIM, GMSD, SCQI and VSI, etc.…”
MethodDeep Local and Global Spatiotemporal Feature Aggregation for Blind Video Quality Assessment
Zhou, W., & Chen, Z. (2020) · IEEE International Conference on Visual Communications and Image Processing (VCIP) · doi:10.1109/vcip49819.2020.9301764 · Cited by 22
“As shown in Table 1, the proposed method is compared with 14 state-of-the-art quality assessment metrics, including PSNR, SSIM [4], MS-SSIM [5], FSIM [6], MOVIE [7], ST-MAD [8], ViS3 [3], JVQ [9], VQM [10], STRRED [11], V-CORNIA [12], V-BLIINDS [14], VIIDEO [16], and DeepBVQA [17].”
MethodInfluentialDepth Map Refinement for Immersive Video
Mieloch, D., Dziembowski, A., & Domański, M. (2021) · IEEE Access · doi:10.1109/access.2021.3050554 · Cited by 14
“Four objective quality metrics are reported: Y-PSNR, VMAF [51], MS-SSIM [52], and IV-PSNR [53].”
DSPNet: Deep Learning-Enabled Blind Reduction of Speckle Noise
Lu, Y., Yang, M., & Liu, R. W. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9413017 · Cited by 15
“Its core part is the multi-scale structural similarity (MS-SSIM) [34], which is essentially a multi-scale extension of SSIM [35].”
BackgroundSpline-based medial axis transform representation of binary images
Wang, J., Kosinka, J., & Telea, A. C. (2021) · Computers & Graphics · doi:10.1016/j.cag.2021.05.012 · Cited by 14
“The Jaccard similarity coeffi-cient [46] achieves this by considering the size of the intersection, normalized by the size of the union, of two shapes The Multi-Scale Structural SIMilarity (MS-SSIM) index [47,48] provides an advanced top-down model of how the human visual system interprets images.”
MethodAudio-Driven Talking Video Frame Restoration
Cheng, H. H., Guo, Y., Yin, J., Chen, H., Wang, J., & Nie, L. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3118287 · Cited by 17
“WeemployedthecommonlyusedreconstructionmetricsPeak Signal-to-Noise Ratio (PSNR) [40], Structural Similarity Index Measure (SSIM) [41], and Multiscale Structural Similarity Index Measure(MS-SSIM) [42] to evaluate the generalization quality of the restored frames.”
BackgroundBVI-CC: A Dataset for Research on Video Compression and Quality Assessment
Katsenou, A., Zhang, F., Afonso, M., Dimitrov, G., & Bull, D. (2022) · Frontiers in Signal Processing · doi:10.3389/frsip.2022.874200 · Cited by 33
A Two-Level Dynamic Adaptive Network for Medical Image Fusion
Huang, W., Zhang, H., Quan, X., & Wang, J. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3169546 · Cited by 20
Low-Light Image Enhancement Using Image-to-Frequency Filter Learning
Sobbahi, R. A., & Tekli, J. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-06430-2_58 · Cited by 16
Digital Image Watermarking Method Based on LSB and DWT Hybrid Technique
Ghrare, S. E., Alamari, A. A. M., & Emhemed, H. A. (2022) · IEEE International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA) · doi:10.1109/mi-sta54861.2022.9837586 · Cited by 18
Image quality assessment on image haze removal
Fang, S., Yang, J., Zhan, J., et al. (2011) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc.2011.5968254 · Cited by 15
Progressive Edge Detection on multi-bit images using polynomial-based binarization
Govindarajani, B., Panett, K., & Agaian, S. С. (2008) · International Conference on Machine Learning and Cybernetics · doi:10.1109/icmlc.2008.4621051 · Cited by 14
Evaluation of floating point image compression
Richter, T. (2009) · International Workshop on Quality of Multimedia Experience (QoMEX) · doi:10.1109/qomex.2009.5246947 · Cited by 16
Ranks for Pairs of Spatial Fields via Metric Based on Grayscale Morphological Distances
Sagar, B. S. D., & Lim, S. L. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2390135 · Cited by 14
Rezazadeh, S., & Coulombe, S. (2009) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2009.5413886 · Cited by 15
Image quality assessment via spatial structural analysis
Yang, X., Sun, Q., & Wang, T. (2016) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2016.08.014 · Cited by 14
Full-reference quality assessment of stereoscopic images by modeling binocular rivalry
Chen, M.-J., Su, C.-C., Kwon, D.-K., Cormack, L. K., & Bovik, A. C. (2012) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/acssc.2012.6489106 · Cited by 15
“It is clear from Table 1 that MS-SSIM delivers the best performance among the three 2D QA algorithms when embedded in the “cyclopean” model.”
MethodSelf-citationA novel adaptive quantization method for video coding
Xiang, G., Jia, H., Yang, M., et al. (2017) · Multimedia Tools and Applications · doi:10.1007/s11042-017-5064-4 · Cited by 14
Perceptual quality evaluation of synthetic pictures distorted by compression and transmission
Kundu, D., Choi, L. K., Bovik, A. C., & Evans, B. L. (2017) · Signal Processing Image Communication · doi:10.1016/j.image.2017.11.004 · Cited by 17
“…objective IQA scores (after non-linear regression), and are also tabulated in Tables 4, 6 and 9 Multi-scale Structural Similarity Index (MS-SSIM) [35] Quarternion Structural Similarity Index (QSSIM) [36] Universal Quality Index (UQI) [37] Human Visual System Visual Difference Predictor (VDP)…”
Self-citationA Just Noticeable Difference-Based Video Quality Assessment Method with Low Computational Complexity
Loh, W.-T., & Bong, D. B. L. (2018) · Sensing and Imaging · doi:10.1007/s11220-018-0216-9 · Cited by 13
“Common examples of weighted pooling are percentile pooling [27], saliency pooling [28], and multiscale pooling [29, 30].”
BackgroundRemoving Atmospheric Turbulence Effects in Unified Complex Steerable Pyramid Framework
Zhang, C., Xue, B., Zhou, F., & Xiong, W. (2018) · IEEE Access · doi:10.1109/access.2018.2883489 · Cited by 14
“To quantitatively evaluate and compare the performance, Table 1 shows the Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Multiscale Similarity Index (MS-SSIM) [31], Spectral Residual-based Similarity Index (SR-SIM) [32] and Feature Similarity Index (FSIM) [33] values for the outputs of the eigh…”
MethodSSVD: Structural SVD-based image quality assessment
Mansouri, A., & Mahmoudi-Aznaveh, A. (2019) · Signal processing. Image communication · doi:10.1016/j.image.2019.01.007 · Cited by 16
Xu, X., Shi, B., Gu, Z., Deng, R., Chen, X., Krylov, A. S., & Ding, Y. S. (2019) · IEEE Access · doi:10.1109/access.2019.2925084 · Cited by 14
“In addition, since different scales will carry out different levels of distortion, utilizing multi-scale framework is beneficial for IQA [27].”
BackgroundTransferring Adaptive Bit Rate Streaming Quality Models from H.264/HD to H.265/4K-UHD
LEBRETON, P., & Yamagishi, K. (2019) · IEICE Transactions on Communications · doi:10.1587/transcom.2019ebp3045 · Cited by 14
“In this analysis, several models were compared: NIQUE [15], GMSD [57], PSNR, PSNR-HVS [58], VIFP [59], SSIM [60], VMAF [13], BRISQUE [14], and MS-SSIM [61].”
MethodModeling of Cumulative QoE in On-Demand Video Services: Role of Memory Effect and Degree of Interest
Duc, T. N., Tran, C. M., Tan, P. X., & Kamioka, E. (2019) · Future Internet · doi:10.3390/fi11080171 · Cited by 14
“STSQ can be predicted using any of the robust video quality assessment (VQA) metrics such as Spatio-Temporal Reduced Reference Entropic Differences (STRRED) [39], Multi-Scale Structural Similarity (MS-SSIM) [40], etc.”
Training Objective Image and Video Quality Estimators Using Multiple Databases
Krasula, L., Baveye, Y., & Callet, P. L. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2935687 · Cited by 16
Distributed Learning and Inference With Compressed Images
Katakol, S., El-Barashy, B. G., Herranz, L., van de Weijer, J., & López, A. M. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3058545 · Cited by 15
“We train the CAR model with the objective of maximising MS-SSIM or PSNR.”
MethodInfluentialA theoretical justification of warping generation for dewarping using CNN
Garai, A., Biswas, S., & Mandal, S. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2020.107621 · Cited by 14
Color Enhancement Using Global Parameters and Local Features Learning
Liu, E., Li, S., & Liu, S. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-69532-3_13 · Cited by 17
“Besides considering the color similarity, we also pay attention to the structure of the image by using a SSIM loss [27] as defined in Eq.”
MethodVisual saliency guided textured model simplification
Yang, B. L., Li, F. W. B., Wang, X., et al. (2015) · The Visual Computer · doi:10.1007/s00371-015-1129-4 · Cited by 14
“We adopt the peak signal-to-noise ratio (PSNR) and multiscale structural similarity index (MS − SSIM) [42] to objectively measure the rendered quality of the textured models.”
MethodCorrelation Maximized Structural Similarity Loss for Semantic SegmentationPreprint
Zhao, S., Wu, B., Chu, W., Hu, Y. G., & Cai, D. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.08711 · Cited by 33
“The mean and variance can be considered as estimates of the lumiance and contrast of the image, and the covariance σ xy measures the tendency of x and y to vary together, thus an indication of structural similarity [41].”
BackgroundMethodFawkes: Protecting Privacy against Unauthorized Deep Learning ModelsPreprint
Shan, S., Wenger, E., Zhang, J., Li, H., Zheng, H.-T., & Zhao, B. Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.08327 · Cited by 338
“In our implementation, | δ ( x , x T ) | is calculated using the DSSIM (Structural Dis-Similarity Index) [61, 62].”
MethodDocScanner: Robust Document Image Rectification with Progressive LearningPreprint
Feng, H., Zhou, W., Deng, J., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.14968 · Cited by 14
“Third, we use Multi-Scale Structural Similarity (MS-SSIM) (Wang et al., 2003) to measure the image similarity between the rectified images and the ground truth undistorted images.”
InfluentialVisible and near‐infrared image fusion based on information complementarity
Li, Z., Pu, S., Ji, M., et al. (2024) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.12378 · Cited by 13
Raeisi, Z., Lashaki, R. A., Deldadehasl, M., Golkarieh, A., & mohammadi, M. M. (2025) · Discover Applied Sciences · doi:10.1007/s42452-025-07163-2 · Cited by 18
De-speckling of medical ultrasound image using metric-optimized knowledge distillation
Khalifa, M., Hamza, H. M., & Hosny, K. M. (2025) · Scientific Reports · doi:10.1038/s41598-025-07115-1 · Cited by 16
Neural Distributed Source Coding
Whang, J., Nagle, A., Acharya, A., Kim, H., & Dimakis, A. G. (2024) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2024.3412976 · Cited by 38
Evaluating GANs in Medical Imaging
Tronchin, L., Sicilia, R., Cordelli, E., Ramella, S., & Soda, P. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-88210-5_10 · Cited by 28
Deep-Learning-Aided Wireless Video Transmission
Tung, T.-Y., & Gündüz, D. (2022) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc51304.2022.9833990 · Cited by 13
“We measure the average quality of the reconstructed video using two metrics: peak signal-to-noise ratio (PSNR) and MS-SSIM [16].”
MethodChakareski, J., Corbillon, X., Simon, G., & Swaminathan, V. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3201397 · Cited by 13
“…Y-PSNR video quality evaluation and comparison that we carry out here, we also investigate the Multiscale - Structural Similarity Metric (MS-SSIM) [44] applied to the delivered viewport video signal (its luminance component) by each of the three methods under comparison, in the case of the 360 ◦…”
MethodPS2 F: Polarized Spiral Point Spread Function for Single-Shot 3D Sensing
Ghanekar, B., Saragadam, V., Mehra, D., et al. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3202511 · Cited by 13
“We compare the PSFs depth estimation using the Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the multi-scale Structural Similarity Index Measure [50] (MS-SSIM) metrics.”
MethodEnd-to-End Optimized Image Compression With Deep Gaussian Process Regression
Cao, M., Dai, W., Li, S., Li, C., Zou, J., Chen, Y., & Xiong, H. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3209661 · Cited by 18
“…with two commonly used metrics, i.e. , mean square error (MSE, d ( x , ˆ x ) = || x − ˆ x || 22 ) and multiscale structural similarity (MS-SSIM [53], d ( x , ˆ x The bit-rate of ˆ y is estimated with a weighted summation of three distributions from three AR-DGPR models in each Authorized…”
Ultrafast Ultrasound Localization Microscopy by Conditional Generative Adversarial Network
Gu, W., Li, B., Luo, J., Yan, Z., Ta, D., & Liu, X. (2022) · IEEE Transactions on Ultrasonics Ferroelectrics and Frequency Control · doi:10.1109/tuffc.2022.3222534 · Cited by 13
“To quantitatively demonstrate the advantages of ULM-GAN; here, resolution scaled error (RSE) [48], MS-SSIM [45], recall metric [49], and dice similarity coefficient (DICE) [25] are calculated, respectively.”
BackgroundMethodInfluentialCoupled-Learning GAN for Inversion of GPR Pipe Images
Xu, T., Yuan, D., Sun, W., et al. (2023) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2023.3274681 · Cited by 13
“During the dielectric constant inversion stage, we adapted a loss function that combines mean absolute error (MAE) and MS-structural similarity (SSIM) losses [12], [13], which can be expressed as follows:”
MethodMPAI-EEV: Standardization Efforts of Artificial Intelligence Based End-to-End Video Coding
Jia, C., Ye, F., Dong, F., Lin, K., Chiariglione, L., Ma, S., Sun, H., & Gao, W. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3310188 · Cited by 15
“Two different sets of values for λ are {2048,1024,512,256} for PSNR and {64,32,16,8} for MS-SSIM [34], respectively.”
BackgroundSparse-to-Dense: High Efficiency Rate Control for End-to-End Scale-Adaptive Video Coding
Chen, J., Wang, M., Zhang, P., et al. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3313611 · Cited by 13
“To evaluate the efficiency of the proposed method, the rate-distortion performance is measured wherein the distortion is evaluated with the PSNR and MS-SSIM [34].”
MethodFGC-VC: Flow-Guided Context Video Compression
Wang, Y., Huang, Q., Tang, B., Sun, H., & Guo, X. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10222501 · Cited by 15
Ahilan, A., Khanth, B. P., Ezhilarasi, R., et al. (2023) · Signal Image and Video Processing · doi:10.1007/s11760-023-02814-6 · Cited by 13
Swain, B. R., Cho, D.-H., Park, J. P., Roh, J., & Ko, J. (2023) · Materials · doi:10.3390/ma16237254 · Cited by 15
“Considering the unique challenges that we mentioned before in steel image segmentation, we used a combined loss function of Focal Loss [37], Jaccard Loss [38], and Multi-Scale Structural Similarity (MS-SSIM) Loss [39].”
MethodLow-Dose 4D-STEM Tomography for Beam-Sensitive Nanocomposites
Hugenschmidt, M., Jannis, D., Kadu, A. A., Grünewald, L., Marchi, S. D., Pérez‐Juste, J., Verbeeck, J., Aert, S. V., & Bals, S. (2023) · ACS Materials Letters · doi:10.1021/acsmaterialslett.3c01042 · Cited by 14
Short-Time Coherent–Incoherent Synthetic Aperture Radar Processing for a Handheld Imaging System
Álvarez-Narciandi, G., Laviada, J., & Las‐Heras, F. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3352706 · Cited by 13
“…the image artifacts generated by tracking errors, but also that the value of M can be tuned to find a tradeoff between the resolution loss derived from the incoherent processing and the artifacts due to tracking errors, which depend on the accuracy of the tracking system used in the scanner.”
MethodProj2Proj: self-supervised low-dose CT reconstruction
Unal, M. O., Ertaş, M., & Yıldırım, İ. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.1849 · Cited by 13
“In addition to these methods, another BM3D (sigma = 0.20) reconstructor was used in the comparisons which gives the highest SSIM ( Wang, Simoncelli & Bovik, 2003 ) for the validation set.”
MethodInfluentialInterference Suppressed NOMA for Semantic-Aware Communication Networks
Zhang, Y., Zhong, R., Liu, Y., Xu, W., & Zhang, P. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3371775 · Cited by 17
“Following the previous works of semantic-enabled image transmission, peak signal-to-noise ratio (PSNR) and MS-SSIM [26] are adopted to measure the quality of the reconstructed images [11], [27].”
MethodExploring Adversarial Robustness of Vision Transformers in the Spectral Perspective
Kim, G., Kim, J., & Lee, J. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00393 · Cited by 28
“…enable representation of the attack strength commonly across different attacks introduced in the previous section, including PSNR, multi-scale structural similarity index measure (MS-SSIM) [39], mean deviation similarity index (MDSI) [40], and learned perceptual image patch similarity (LPIPS) [41].”
BackgroundA Convolution Modulation Jamming Method Based on the Optimal Combination of Noise Templates
Wang, Y., Liu, G., Ma, X., et al. (2024) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2024.3386976 · Cited by 14
“In this letter, the multiscale structural similarity (MS-SSIM) index is utilized to evaluate the jamming effect of noise templates with different scales comprehensively [10], [11].”
MethodZhang, G., Gu, W., Yue, Y., et al. (2024) · IEEE Transactions on Ultrasonics Ferroelectrics and Frequency Control · doi:10.1109/tuffc.2024.3388102 · Cited by 13
NLIC: Non-Uniform Quantization-Based Learned Image Compression
Ge, Z., Ma, S., Gao, W., Pan, J., & Jia, C. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3401872 · Cited by 22
“…[19], [20], [21], [22] outperform the state-of-the-art traditional standardized codec VVC Test Model (VTM) [3] in terms of Rate-Distortion (R-D) performance in a variety of quality metrics such as Peak-Signal-to-Noise-Ratio (PSNR) and Multi-Scale Structural Similarity Index Metric (MS-SSIM) [23].”
BackgroundDiffPlate: A Diffusion Model for Super-Resolution of License Plate Images
AlHalawani, S., Benjdira, B., Ammar, A., Koubâa, A., & Ali, A. M. (2024) · Electronics · doi:10.3390/electronics13132670 · Cited by 19
“In order to assess the quality of our model comprehensively, we used the following metrics: Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM) [32] and Multi-scale Structural Similarity (MS-SSIM) [33].”
MethodInfluentialSaleh, A. H., Atila, Ü., & Menemencioğlu, O. (2024) · International Journal of Imaging Systems and Technology · doi:10.1002/ima.23152 · Cited by 18
Valsesia, D., Bianchi, T., & Magli, E. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3465043 · Cited by 18
“Table III reports the lossless rate reduction compared to CCSDS for the M configuration in two settings of interest: zero-shot transfer , i.e., the model trained on HySpecNet-11k is used as is on PRISMA, and after finetuning with 100 PRISMA images.”
MethodTask-Aware Encoder Control for Deep Video Compression
Ge, X., Luo, J., Zhang, X., Xu, T., Lu, G. S., He, D., Geng, J., Wang, Y., Zhang, J., & Qin, H. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.02460 · Cited by 24
“Recently, a number of learning-based video codecs [14, 18, 24, 25, 29, 35] have been proposed, designed based on residual coding or conditional coding, achieved better and better pixel-wise signal quality metrics, e.g., PSNR and MS-SSIM [41], which mainly serve the human visual experience.”
BackgroundMethodTong, C., Natgunanathan, I., Xiang, Y., Li, J., Zong, T., Zheng, X., & Gao, L. (2024) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2024.3486206 · Cited by 15
FabricDiffusion: High-Fidelity Texture Transfer for 3D Garments Generation from In-The-Wild Images
Zhang, C., Wang, Y., Vicente, F., et al. (2024) · SIGGRAPH Asia Conference Papers · doi:10.1145/3680528.3687637 · Cited by 13
“We evaluate the quality of generated textures and garments using commonly used metrics: LPIPS [Zhang et al. 2018] , SSIM [Wang et al. 2004], MS-SSIM [Wang et al. 2003], DISTS [Ding et al. 2020], and FLIP [Andersson et al. 2020].”
A Comprehensive Survey on Real-Time Image Super-Resolution for IoT and Delay-Sensitive Applications
Rasool, M. J. A., Ahmad, S., Mardieva, S., Akter, S., & Whangbo, T. K. (2024) · Applied Sciences · doi:10.3390/app15010274 · Cited by 21
Advances in artificial intelligence: a review for the creative industries
Anantrasirichai, N., Zhang, F., & Bull, D. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11494-w · Cited by 107
Liu, Y., Yang, Q., Zhang, Y., Xu, Y., Yang, L., Xu, X., & Liu, S. (2025) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2025.3541862 · Cited by 26
“We thus only need to find α R such that the estimated decimal degree of confidence for an unseen sample x i , whose quality level was found to be equal to j , can be calculated using Combining this result with the obtained quality level yields the final estimate of the continuous quality score for a…”
ECVC: Exploiting Non-Local Correlations in Multiple Frames for Contextual Video Compression
Jiang, W., Li, J., Zhang, K., & Zhang, L. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.00687 · Cited by 25
“In ablation studies, all models are optimized with MSE, and PSNR is adopted to evaluate distortion. tions, which effectively improves the rate-distortion performance.”
Recent Advances in Image Quality Assessment
Zhai, G. (2014) · Springer eBooks · doi:10.1007/978-3-319-10368-6_3 · Cited by 13
Attack and Improvement of the Fidelity Preserved Fragile Watermarking of Digital Images
Li, M., Xiao, D., & Zhang, Y. (2015) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-015-1941-1 · Cited by 13
“…with human perception of image distortions and subjective quality ratings [18], various advanced metrics apart from the PSNR, such as SSIM [19], MS-SSIM [20], FSIM [21], and CISI [22], are applied in order to verify the impact of the proposed approach on the image quality in a more reliable way.”
MethodQuality prediction of asymmetrically compressed stereoscopic videos
Wang, J., Wang, S., & Wang, Z. (2015) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2015.7351440 · Cited by 13
Self-citationFast Inverse Tone Mapping Based on Reinhard's Global Operator with Estimated Parameters
Kinoshita, Y., Shiota, S., & Kiya, H. (2017) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1587/transfun.e100.a.2248 · Cited by 13
Multistage Pooling for Blind Quality Prediction of Asymmetric Multiply-Distorted Stereoscopic Images
Shao, F., Gao, Y., Jiang, Q., Jiang, G., & Ho, Y. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2817072 · Cited by 14
Source Coding Options to Improve HEVC Video Streaming in Vehicular Networks
Garrido, P., Malumbres, M. P., Piñol, P., et al. (2018) · Sensors · doi:10.3390/s18093107 · Cited by 13
“In the literature, we can find quality assessment metrics that better correlates with human perceived quality like MS-SSIM [30].”
BackgroundNN-Based Prediction of Sentinel-1 SAR Image Filtering Efficiency
Rübel, Lukin, & Egiazarian (2019) · Géosciences · doi:10.3390/geosciences9070290 · Cited by 11
“Visual quality metrics resulted from SSIM, such as FSIM [29], MSSSIM [50], IW-SSIM [51], ADD-SSIM [52], ADD-GSIM [52], SSIM4 [49].”
MethodDeep Color Transfer for Color-Plus-Mono Dual Cameras
Jang, H. W., & Jung, Y. J. (2020) · Sensors · doi:10.3390/s20092743 · Cited by 14
“where p is the pixel position and the SSIM is a similarity metric that is generally computed with a window size of 11 × 11 at a pixel position p [23].”
MethodAk, A., Ling, S., & Callet, P. L. (2020) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew46912.2020.9105975 · Cited by 18
“3075 MSSIM [25] 0.”
ResultOkarma, K., Fastowicz, J., Lech, P., & Лукин, В. В. (2020) · Applied Sciences · doi:10.3390/app10186248 · Cited by 14
“Abbreviations The following abbreviations are used in this manuscript: ABS Acrylonitrile butadiene styrene ADD-GSIM Analysis of distortion distribution-based Gradient SIMilarity ADD-SSIM Analysis of distortion distribution-based Structural SIMilarity CAD Computer-Aided Design CISI Combined Image Similarity Index CSF C…”
MethodInfluential
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.