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 101–200 of 6,047
From QoS to QoE: A Tutorial on Video Quality Assessment
Chen, Y., Wu, K., & Zhang, Q. (2015) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2014.2363139 · Cited by 330
Objective quality assessment of multiply distorted images
Jayaraman, D., Mittal, A., Moorthy, A. K., & Bovik, A. C. (2012) · 2012 Conference Record of the Forty Sixth Asilomar Conference on Signals, Systems and Computers (ASILOMAR) · doi:10.1109/acssc.2012.6489321 · Cited by 322
Self-citationConcolic testing for deep neural networks
Sun, Y., Wu, M., Ruan, W., Huang, X., Kwiatkowska, M., & Kroening, D. (2018) · Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering · doi:10.1145/3238147.3238172 · Cited by 332
Study of Subjective and Objective Quality Assessment of Audio-Visual Signals
Min, X., Zhai, G., Zhou, J., Farias, M. C. Q., & Bovik, A. C. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2988148 · Cited by 328
“Likewise, auditory masking principles are well-understood, and simultaneous masking is embodied by VQA models like SSIM and MS-SSIM [8], [9].”
BackgroundMethodInfluentialSelf-citationUncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild
Zhang, W., Ma, K., Zhai, G., & Yang, X. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3061932 · Cited by 327
A Haar wavelet-based perceptual similarity index for image quality assessment
Reisenhofer, R., Bosse, S., Kutyniok, G., & Wiegand, T. (2018) · Signal Processing: Image Communication · doi:10.1016/j.image.2017.11.001 · Cited by 312
Video Compression Through Image Interpolation
Wu, C.-Y., Singhal, N., & Krähenbühl, P. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01237-3_26 · Cited by 316
“Our deep video codec outperforms all deep learning baselines, MPEG-4 Part 2, and H.261 in both compression rate and visual quality measured by MS-SSIM [29] and PSNR.”
MethodScale-Space Flow for End-to-End Optimized Video Compression
Agustsson, E., Minnen, D., Johnston, N., Ballé, J., Hwang, S. J., & Toderici, G. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00853 · Cited by 317
“Recently, there has been significant progress in the area of end-to-end optimized image compression, which went from barely matching JPEG [33] to methods such as [8, 26, 5] that can outperform the best hand-engineered codecs when evaluated in terms of multi-scale structural similarity (MS-SSIM) [36], PSNR, and subject…”
BackgroundMethodU-Net-Based Medical Image Segmentation
Yin, X.-X., Sun, L., Fu, Y., Lu, R., & Zhang, Y. (2022) · Journal of Healthcare Engineering · doi:10.1155/2022/4189781 · Cited by 318
RetractedUGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content
Tu, Z., Wang, Y., Birkbeck, N., Adsumilli, B., & Bovik, A. C. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3072221 · Cited by 363
Self-citationDiving deeper into underwater image enhancement: A survey
Anwar, S., & Li, C. (2020) · Signal Processing: Image Communication · doi:10.1016/j.image.2020.115978 · Cited by 317
“The channels are then subjected to different size of sliding windows to compute the SSIM loss between the turbid and generated images.”
BackgroundInfluentialEDRNet: Encoder–Decoder Residual Network for Salient Object Detection of Strip Steel Surface Defects
Song, G., Song, K., & Yan, Y. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3002277 · Cited by 309
“SSIM [56] is originally used for image quality assessment, which measures the structural similarity between the predicted saliency map and the ground truth.”
BackgroundMethodState representation learning for control: An overview
Lesort, T., Díaz-Rodríguez, N., Goudou, J.-F., & Filliat, D. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.07.006 · Cited by 301
Saliency-Guided Quality Assessment of Screen Content Images
Gu, K., Wang, S., Yang, H., Lin, W., Zhai, G., Yang, X., & Zhang, W. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2547343 · Cited by 303
Image super-resolution: A comprehensive review, recent trends, challenges and applications
Lepcha, D. C., Goyal, B., Dogra, A., & Goyal, V. (2023) · Information Fusion · doi:10.1016/j.inffus.2022.10.007 · Cited by 305
End-to-End Variational Networks for Accelerated MRI Reconstruction
Sriram, A., Zbontar, J., Murrell, T., Defazio, A., Zitnick, C. L., Yakubova, N., Knoll, F., & Johnson, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-59713-9_7 · Cited by 301
“…of the CNN in each cascade along with the η t s, are estimated from the training data by minimizing the structural similarity loss, J (ˆ x , x ∗ ) = − SSIM(ˆ x , x ∗ ) , where SSIM is the Structural Similarity index [16] and ˆ x , x ∗ are the reconstruction and ground truth images, respectively.”
MethodThe Devil Is in the Details: Window-based Attention for Image Compression
Zou, R., Song, C., & Zhang, Z. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01697 · Cited by 300
“…auto-encoder (VAE) [24] has achieved better rate-distortion [41] performance than conventional lossy image compression methods on metrics of Signal-to-Noise Ratio (PSNR) and Multi-Scale-Structural Similarity Index Measure (MS-SSIM) [46], showing great potential for practical compression use.”
BackgroundRodríguez-Barroso, N., Jiménez-López, D., Luzón, M. V., Herrera, F., & Martínez-Cámara, E. (2023) · Information Fusion · doi:10.1016/j.inffus.2022.09.011 · Cited by 296
“5 and the Multi-Scale Structural Similarity (SSIM) [168] is greater than 0.”
BackgroundInfluentialBlind Image Quality Assessment Using a General Regression Neural Network
Li, C., Bovik, A. C., & Wu, X. (2011) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2011.2120620 · Cited by 290
“Similarity index (MS-SSIM) [ 2 ] and its variants [9], the visual information fidelity index [10], and the visual several prominent FR objective metrics have been demonstrated to have much higher correlation”
MethodSelf-citationAggregated Contextual Transformations for High-Resolution Image Inpainting
Zeng, Y., Fu, J., Chao, H., & Guo, B. (2023) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2022.3156949 · Cited by 290
“We can find in the quantitative comparison in Table 1 that, PConv [44] wins second place in terms of L 1 error, PSNR and SSIM.”
ResultInfluentialCompressAI: a PyTorch library and evaluation platform for end-to-end compression research
Bégaint, J., Racapé, F., Feltman, S., & Pushparaja, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.03029 · Cited by 284
“: MS-SSIM [12]).”
MethodInfluentialReduced- and No-Reference Image Quality Assessment
Wang, Z., & Bovik, A. (2011) · IEEE Signal Processing Magazine · doi:10.1109/msp.2011.942471 · Cited by 280
Self-citationCrowd Counting With Deep Structured Scale Integration Network
Liu, L., Qiu, Z., Li, G., Liu, S., Ouyang, W., & Lin, L. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00186 · Cited by 290
“We ameliorate the original MS-SSIM [39] with dilation operations to enlarge the diversity of the sizes of local regions and force our network to capture the local correlation within regions of different sizes.”
BackgroundMethodInfluentialVariable Rate Deep Image Compression With a Conditional Autoencoder
Choi, Y., El-Khamy, M., & Lee, J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00324 · Cited by 274
“In Figure 9, we compare our variable-rate networks optimized for MSE, MS-SSIM and combined MSE+MS-SSIM losses, respectively.”
MethodInfluentialState-of-the-Art in 360° Video/Image Processing: Perception, Assessment and Compression
Xu, M., Li, C., Zhang, S., & Callet, P. L. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.2966864 · Cited by 281
Blind image quality assessment by relative gradient statistics and adaboosting neural network
Liu, L., Hua, Y., Zhao, Q., Huang, H., & Bovik, A. C. (2016) · Signal Processing: Image Communication · doi:10.1016/j.image.2015.10.005 · Cited by 282
“In order to take into account the multiscale character of natural images, of image distortions, and of visual perception [11,17], we also downsample the image by a factor of 2, then compute the same three features yielding a 6dimensional feature vector (3 features at each scale).”
MethodSelf-citationImage Quality Assessment Using Contrastive Learning
Madhusudana, P. C., Birkbeck, N., Wang, Y., Adsumilli, B., & Bovik, A. C. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3181496 · Cited by 285
Self-citationFast Dynamic Radiance Fields with Time-Aware Neural Voxels
Fang, J., Yi, T., Wang, X., Xie, L., Zhang, X., Liu, W., Nießner, M., & Tian, Q. (2022) · SIGGRAPH Asia 2022 Conference Papers · doi:10.1145/3550469.3555383 · Cited by 285
Jayasankar, U., Thirumal, V., & Ponnurangam, D. (2021) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2018.05.006 · Cited by 279
“The metrics used for image compression are CR, PSNR, MSE, RMSE, SSIM, MS-SSIM, bpp (bits per pixel), etc. are employed.”
DeepLPF: Deep Local Parametric Filters for Image Enhancement
Moran, S., Marza, P., McDonagh, S., Parisot, S., & Slabaugh, G. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01284 · Cited by 278
“MS-SSIM is the multi-scale structural similarity [26], and ω lab , ω ms-ssim are hyperparameters weighting the relative influence of the terms in the loss function.”
Reduced-Reference Image Quality Assessment by Structural Similarity Estimation
Rehman, A., & Wang, Z. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2197011 · Cited by 272
“Color versions of one or more of the figures in this paper are available online at http://ieeexplore.ieee.org.”
BackgroundSelf-citationDeep Learning of Human Visual Sensitivity in Image Quality Assessment Framework
Kim, J., & Lee, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.213 · Cited by 265
“DeepQA was compared to eight FR-IQA metrics: PSNR, SSIM [32], MS-SSIM [33], VIF [28], GMSD [34], FSIMc [35], DOG-SSIMc [17], and FR-DCNN [14].”
MethodA comprehensive assessment of the structural similarity index
Dosselmann, R., & Yang, X. D. (2011) · Signal, Image and Video Processing · doi:10.1007/s11760-009-0144-1 · Cited by 275
FVC: A New Framework towards Deep Video Compression in Feature Space
Hu, Z., Lu, G., & Xu, D. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00155 · Cited by 273
“In our proposed framework, we optimize the following Rate Distortion (RD) trade-off: where R o and R r denote the numbers of bits used to encode the offset map O t and the residual feature map R t , respectively. d ( X t , ˆ X t ) denotes the distortion between the input frame X t and the reconstructed frame ˆ X t , w…”
BackgroundMethodInfluentialObjective Quality Evaluation of Dehazed Images
Min, X., Zhai, G., Gu, K., Yang, X., & Guan, X. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2018.2868771 · Cited by 269
“Given an image I, we first compute the local mean and variance [27]–[29]”
BackgroundMethodNo-Reference Quality Assessment of Natural Stereopairs
Chen, M.-J., Cormack, L. K., & Bovik, A. C. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2267393 · Cited by 268
“The quality scores are computed using the 2D FR QA indices C4 [27] and SSIM [28], then combined to produce a final predicted 3D QA score.”
MethodResultSelf-citationStructurally-Sensitive Multi-Scale Deep Neural Network for Low-Dose CT Denoising
You, C., Cong, W., Wang, G., Yang, Q., Shan, H., Gjesteby, L., Li, G., Ju, S., Zhang, Z., Zhao, Z., et al. (2018) · IEEE Access · doi:10.1109/access.2018.2858196 · Cited by 259
“To measure the structural and perceptual similarity between two images, the SSIM [49] is formulated as follows: SSIM(x, z) = 2µxµz + C1 µ2x + µ 2 z + C1 ∗ 2σxz + C2 σ2x + σ 2 z + C2 (6) = l(x, z) ∗ cs(x, z) (7) where C1,C2 are constants and µx,µz ,σx,σz ,σxz denote means, standard deviations and cross-covariance of th…”
InfluentialEnd-to-end optimization of nonlinear transform codes for perceptual quality
Ballé, J., Laparra, V., & Simoncelli, E. P. (2016) · 2016 Picture Coding Symposium (PCS) · doi:10.1109/pcs.2016.7906310 · Cited by 261
Self-citationNeural Scene Graphs for Dynamic Scenes
Ost, J., Mannan, F., Thuerey, N., Knodt, J., & Heide, F. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00288 · Cited by 263
“For PSNR and SSIM, higher is better; for LPIPS lower is better.”
MethodSR-SIM: A fast and high performance IQA index based on spectral residual
Zhang, L., & Li, H. (2012) · 2012 19th IEEE International Conference on Image Processing · doi:10.1109/icip.2012.6467149 · Cited by 256
Wireless Deep Video Semantic Transmission
Wang, S., Dai, J., Liang, Z., Niu, K., Si, Z., Dong, C., Qin, X., & Zhang, P. (2023) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3221977 · Cited by 263
“For the reconstruction task, we optimize DVST in terms of the mean squared error (MSE) for the peak-signal-to-noise ratio (PSNR) metric, or multiscale structural similarity [39] (MS-SSIM) for perceptual quality.”
MethodTOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment
Chen, C., Mo, J., Hou, J., Wu, H., Liao, L., Sun, W., Yan, Q., & Lin, W. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3378466 · Cited by 276
“The parallel methods, such as MS-SSIM, have difficulties in extracting semantic representations.”
MethodInfluentialPerceptual Quality Metric With Internal Generative Mechanism
Wu, J., Lin, W., Shi, G., & Liu, A. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2214048 · Cited by 258
“1333] [35], which is obtained through psychophysical experiment.”
Dynamic range independent image quality assessment
Aydin, T. O., Mantiuk, R., Myszkowski, K., & Seidel, H.-P. (2008) · ACM Transactions on Graphics · doi:10.1145/1360612.1360668 · Cited by 259
Pixel Recursive Super Resolution
Dahl, R., Norouzi, M., & Shlens, J. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.581 · Cited by 246
“Many methods exist for quantifying image similarity that attempt to measure human perception judgements of similarity [45, 46, 28].”
Predicting the Perceptual Quality of Point Cloud: A 3D-to-2D Projection-Based Exploration
Yang, Q., Chen, H., Ma, Z., Xu, Y., Tang, R., & Sun, J. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.3033117 · Cited by 256
“Recently, Alexiou et al. [36] attempted to correlate the perceptual quality with respect to the weighted objective index (such as PSNR, MS-SSIM [18], etc) of projected image planes, where experimental studies had shown that there was no clear MOS prediction performance improvement when having more…”
BackgroundMethodInfluentialA Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
Gui, J., Sun, Z., Wen, Y., Tao, D., & Ye, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.06937 · Cited by 253
“Different from single scale SSIM measure, the MS-SSIM [222] is proposed for multiscale image quality assessment.”
MethodHyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing
Alaluf, Y., Tov, O., Mokady, R., Gal, R., & Bermano, A. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01796 · Cited by 259
“Along with the inference time of each method, we report the pixel-wise L2 distance, the LPIPS [72] distance, and the MS-SSIM [66] score between each reconstruction and source.”
MethodQuality Evaluation of Image Dehazing Methods Using Synthetic Hazy Images
Min, X., Zhai, G., Gu, K., Zhu, Y., Zhou, J., Guo, G., Yang, X., Guan, X., & Zhang, W. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2902097 · Cited by 252
“Since the proposed method follows the framework of FR IQA, we compare it with 10 state-of-the-art FR IQA measures, including PSNR, SSIM [21], MS-SSIM [32], VIF [33], MAD [34], IW-SSIM [35], GSI [36], FSIM [37], IFC [38], and PSIM [39].”
BackgroundMethodInfluentialLossy Image Compression with Compressive Autoencoders
Theis, L., Shi, W., Cunningham, A., & Huszár, F. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.00395 · Cited by 230
“We used the implementation of van der Walt et al. (2014) for SSIM and the implementation of Toderici et al. (2016b) for MS-SSIM.”
BackgroundMethodInfluentialImage Quality Assessment by Separately Evaluating Detail Losses and Additive Impairments
Li, S., Zhang, F., Ma, L., & Ngan, K. N. (2011) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2011.2152382 · Cited by 250
Invisible steganography via generative adversarial networks
Zhang, R., Dong, S., & Liu, J. (2019) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6951-z · Cited by 250
“Inspired by their work, we introduce the structure similarity index (SSIM) [17] and its variant, the multi-scale structure similarity index (MS-SSIM) [18] into our metric.”
MethodGu, K., Wang, S., Zhai, G., Ma, S., Yang, X., Lin, W., Zhang, W., & Gao, W. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2518868 · Cited by 244
No-Reference Quality Assessment of Screen Content Pictures
Gu, K., Zhou, J., Qiao, J.-F., Zhai, G., Lin, W., & Bovik, A. C. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2711279 · Cited by 242
Self-citationDeep Convolutional AutoEncoder-based Lossy Image Compression
Cheng, Z., Sun, H., Takeuchi, M., & Katto, J. (2018) · 2018 Picture Coding Symposium (PCS) · doi:10.1109/pcs.2018.8456308 · Cited by 241
“The quality of the reconstructed images is measured using the quality metrics PSNR and MSSSIM [12], which measure the objective quality and perceived quality, respectively.”
Wirtinger holography for near-eye displays
Chakravarthula, P., Peng, Y., Kollin, J., Fuchs, H., & Heide, F. (2019) · ACM Transactions on Graphics · doi:10.1145/3355089.3356539 · Cited by 239
“4.1): 1) ℓ 2 -norm least-squares objective 2) MS-SSIM [Wang et al. 2003] error minimization as a hand-crafted perceptual accuracy 3) the learned perceptual similarity metric [Zhang et al. 2018] Figure 6 shows evaluations on a custom dataset of 20 images randomly picked from Set5, Set14, Urban100…”
BackgroundInfluentialA Fast Reliable Image Quality Predictor by Fusing Micro- and Macro-Structures
Gu, K., Li, L., Lu, H., Min, X., & Lin, W. (2017) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2017.2652339 · Cited by 237
A Deep Learning based No-reference Quality Assessment Model for UGC Videos
Sun, W., Min, X., Lu, W., & Zhai, G. (2022) · Proceedings of the 30th ACM International Conference on Multimedia · doi:10.1145/3503161.3548329 · Cited by 240
“Some existing work [38][25][20] shows that considering the multi-scale characteristics can improve the performance of image quality assessment.”
BackgroundPerceptual Quality Assessment of Screen Content Images
Yang, H., Fang, Y., & Lin, W. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2465145 · Cited by 238
“Hence, they have been widely investigated in the FR NIQA.”
BackgroundAutomatic Contrast Enhancement Technology With Saliency Preservation
Gu, K., Zhai, G., Yang, X., Zhang, W., & Chen, C. W. (2015) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2014.2372392 · Cited by 235
“[41] values computed on predicted and disorderly regions with psychophysical parameters [42]; 4) structural similarity weighted (SW) SSIM (SW-SSIM) [23], estimating weights in a block-based manner for improving SSIM.”
MethodBallé, J., Chou, P. A., Minnen, D., Singh, S., Johnston, N., Agustsson, E., Hwang, S. J., & Toderici, G. (2021) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.3034501 · Cited by 231
“d image compression models with JPEG (JPEG 1992) and BPG, a variant of HEVC (HEVC 2013), in terms of peak signalto-noise ratio (PSNR) as well as MS-SSIM, a popular perceptual image quality metric (Z. Wang, Simoncelli, and Bovik, 2003). The introduction of FA into NTC leads to a significant improvement of RD performance…”
MethodVariational Approaches for Auto-Encoding Generative Adversarial Networks
Rosca, M., Lakshminarayanan, B., Warde-Farley, D., & Mohamed, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.04987 · Cited by 217
“[29] assess the similarity between class-conditional generated samples using MSSSIM [40], an image similarity metric that has been shown to correlate well with human judgement.”
MethodHybrid No-Reference Quality Metric for Singly and Multiply Distorted Images
Gu, K., Zhai, G., Yang, X., & Zhang, W. (2014) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2014.2344471 · Cited by 227
Rippel, O., Nair, S., Lew, C., Branson, S., Anderson, A., & Bourdev, L. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00355 · Cited by 223
“On the top row of Figure 8, we present the average MS-SSIM across all videos for each dataset and for each codec (Section 5.2), as function of BPP. Relative compressed sizes.”
MethodInfluentialAn End-to-End Learning Framework for Video Compression
Lu, G., Zhang, X., Ouyang, W., Chen, L., Gao, Z., & Xu, D. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2988453 · Cited by 224
Temporal Context Mining for Learned Video Compression
Sheng, X., Li, J., Li, B., Li, L., Liu, D., & Lu, Y. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3220421 · Cited by 226
“Tothebestofourknowledge,thisisthe firstend-to-endlearnedvideocompressionschemeachieving such a milestone result that outperforms HM in terms of peak signal-to-noise ratio (PSNR) and VTM in terms of multi-scale structural similarity index measure (MS-SSIM) [39].”
BackgroundComparison of Full-Reference Image Quality Models for Optimization of Image Processing Systems
Ding, K., Ma, K., Wang, S., & Simoncelli, E. P. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01419-7 · Cited by 224
“MS-SSIM (Wang et al. 2003), the Multi-Scale extension of the SSIM index (Wang et al.”
MethodInfluentialSelf-citationA comprehensive evaluation of full reference image quality assessment algorithms
Zhang, L., Zhang, L., Mou, X., & Zhang, D. (2012) · 2012 19th IEEE International Conference on Image Processing · doi:10.1109/icip.2012.6467150 · Cited by 221
RFSIM: A feature based image quality assessment metric using Riesz transforms
Zhang, L., Zhang, L., & Mou, X. (2010) · 2010 IEEE International Conference on Image Processing · doi:10.1109/icip.2010.5649275 · Cited by 218
Deep CT to MR Synthesis Using Paired and Unpaired Data
Jin, C.-B., Kim, H., Liu, M., Jung, W., Joo, S., Park, E., Ahn, Y., Han, I., Lee, J., & Cui, X. (2019) · Sensors · doi:10.3390/s19102361 · Cited by 224
“It does not merely measure the pixel-wise intensity difference; it also evaluates the luminance, contrast, and structure of the two images, and is defined as follows [34]:”
BackgroundLearning for Video Compression With Hierarchical Quality and Recurrent Enhancement
Yang, R., Mentzer, F., Van Gool, L., & Timofte, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00666 · Cited by 218
“In this paper, the Multi-Scale Structural SIMilarity (MS-SSIM) [36] and the Peak Signalto-Noise Ratio (PSNR) are used to evaluate quality.”
MethodReplacing Mobile Camera ISP with a Single Deep Learning Model
Ignatov, A., Van Gool, L., & Timofte, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00276 · Cited by 215
“The structural similarity (SSIM) loss [60] is used here to increase the”
MethodLoss Functions for Neural Networks for Image Processing
Zhao, H., Gallo, O., Frosio, I., & Kautz, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.08861 · Cited by 214
“We use two state-of-the-art metrics for image quality: the structural similarity index (SSIM [13]) and the multi-scale structural similarity index (MS-SSIM [14]).”
BackgroundMethodAutomatic Prediction of Perceptual Image and Video Quality
Bovik, A. C. (2013) · Proceedings of the IEEE · doi:10.1109/jproc.2013.2257632 · Cited by 214
Self-citationRAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content
Tu, Z., Yu, X., Wang, Y., Birkbeck, N., Adsumilli, B., & Bovik, A. C. (2021) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2021.3090333 · Cited by 215
“Incorporating multiscale information in quality models provides significant performance improvements [8], [77].”
BackgroundSelf-citationWITT: A Wireless Image Transmission Transformer for Semantic Communications
Yang, K., Wang, S., Dai, J., Tan, K., Niu, K., & Zhang, P. (2023) · ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp49357.2023.10094735 · Cited by 218
“For more intuitive observation and comparison, it is converted into the form of dB and the formula is MS-SSIM(dB) = − 10 log(1 − MS-SSIM).”
MethodInfluentialM-LVC: Multiple Frames Prediction for Learned Video Compression
Lin, J., Liu, D., Li, H., & Wu, F. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00360 · Cited by 216
“It requires our future work to optimize our model for MS-SSIM to achieve a better performance in MS-SSIM.”
MethodInfluentialMüller-Franzes, G., Niehues, J. M., Khader, F., Arasteh, S. T., Haarburger, C., Kuhl, C., Wang, T., Han, T., Nolte, T., Nebelung, S., et al. (2023) · Scientific Reports · doi:10.1038/s41598-023-39278-0 · Cited by 214
“Third, the Multiscale Structural Similarity Index Measure (MSSSIM) [27] that is a generalized version of the SSIM [28] by applying SSIM at different resolutions.”
MethodSwinJSCC: Taming Swin Transformer for Deep Joint Source-Channel Coding
Yang, K., Wang, S., Dai, J., Qin, X., Niu, K., & Zhang, P. (2025) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2024.3424842 · Cited by 217
“The multi-scale SSIM (MS-SSIM) [25] provides greater versatility than single-scale SSIM, making it suitable for a broader viewing range.”
SRFeat: Single Image Super-Resolution with Feature Discrimination
Park, S.-J., Son, H., Cho, S., Hong, K.-S., & Lee, S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01270-0_27 · Cited by 205
“However, it is well-known that measuring pixel-wise difference can hardly capture perceptual differences between images [49, 48, 17], thus higher PSNR does not necessarily lead to a per-”
BackgroundMC360IQA: A Multi-channel CNN for Blind 360-Degree Image Quality Assessment
Sun, W., Min, X., Zhai, G., Gu, K., Duan, H., & Ma, S. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2019.2955024 · Cited by 208
“For FR IQA models, it is obvious that the performance of PSNR-based IQA models is remarkably inferior to the traditional successful IQA models like SSIM, MS-SSIM, though they are specially designed for 360-degree images.”
DeepWiVe: Deep-Learning-Aided Wireless Video Transmission
Tung, T.-Y., & Gunduz, D. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3191354 · Cited by 211
“We use the default parameter values of ( α M , β j , γ j ) provided by the original paper [42].”
MethodA subjective study to evaluate video quality assessment algorithms
Seshadrinathan, K., Soundararajan, R., Bovik, A. C., & Cormack, L. K. (2010) · SPIE Proceedings · doi:10.1117/12.845382 · Cited by 210
Self-citationDeep Virtual Reality Image Quality Assessment With Human Perception Guider for Omnidirectional Image
Kim, H. G., Lim, H.-T., & Ro, Y. M. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2898732 · Cited by 203
“(a ) Comparison between MOS values and quality scores by PSNR, (b) quality scores by SSIM [13], (c) quality scores by MS-SSIM [14], (d) quality scores by VIFp [15], (e) quality scores by S-PSNR [17], (f) quality scores by WS-PSNR [16], (g) quality scores by CPP-PSNR [18], and (h) quality scores by…”
MethodHigh-Fidelity Generative Image Compression
Mentzer, F., Toderici, G. D., Tschannen, M., & Agustsson, E. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.09965 · Cited by 206
“, (Multi-Scale) Structural Similarity Index ((MS-)SSIM) [53, 52], Learned Perceptual Image Patch Similarity (LPIPS) [57]), the weakness of each metric is exploited by the learning algorithm, e.”
BackgroundLow Photon Count Phase Retrieval Using Deep Learning
Goy, A., Arthur, K., Li, S., & Barbastathis, G. (2018) · Physical Review Letters · doi:10.1103/physrevlett.121.243902 · Cited by 205
GPRInvNet: Deep Learning-Based Ground-Penetrating Radar Data Inversion for Tunnel Linings
Liu, B., Ren, Y., Liu, H., Xu, H., Wang, Z., Cohn, A. G., & Jiang, P. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2020.3046454 · Cited by 204
“The loss function was calculated as follows [37], [46]:”
MethodSelf-citationMason, A., Rioux, J., Clarke, S. E., Costa, A., Schmidt, M., Keough, V., Huynh, T., & Beyea, S. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2019.2930338 · Cited by 204
“Ten full-reference objective IQMs were included in this study: RMSE, peak signal to noise ratio (PSNR), SSIM, multiscale SSIM (MSSSIM [25]), information-weighted SSIM (IWSSIM [26]), gradient magnitude similarity deviation (GMSD [27]), feature similarity index (FSIM [28]), high dynamic range visible difference predicto…”
MethodHybrid Spatial-Temporal Entropy Modelling for Neural Video Compression
Li, J., Li, B., & Lu, Y. (2022) · Proceedings of the 30th ACM International Conference on Multimedia · doi:10.1145/3503161.3547845 · Cited by 205
“If oriented to MS-SSIM, the corresponding bitrate saving is 35.1%.”
BackgroundInfluentialChen, M., Shao, H., Dou, H., Li, W., & Liu, B. (2023) · IEEE Transactions on Reliability · doi:10.1109/tr.2022.3215243 · Cited by 204
Quality Assessment of Stereoscopic 3D Image Compression by Binocular Integration Behaviors
Lin, Y.-H., & Wu, J.-L. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2302686 · Cited by 200
“Therefore, the gain g L i of the DOG frequency band V L i is defined as: Based on the pre-described BFI process in the ventral stream, we can derive the Frequency-Integrated metric (FI-metric) for computing the visual distortion of a 3D stereo image as: FI-metric = {g L i D(V L i , V L i ) + g R i D(V R i , V R i )},…”
MethodInfluentialHu, J., Liao, X., Wang, W., & Qin, Z. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3074259 · Cited by 195
Neural Head Avatars from Monocular RGB Videos
Grassal, P.-W., Prinzler, M., Leistner, T., Rother, C., Niebner, M., & Thies, J. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01810 · Cited by 200
“For evaluation, we deploy the pixel-wise ℓ1 metric; the reference-free cumulative probability blur detection metric (CPBD) [11]; the multi-scale structural similarity metric (MS-SSIM) [77]; the learned perceptual image patch similarity (LPIPS) [83]; and the cosine distance of a pretrained face recognition network (CSI…”
MethodImage Quality Assessment Using Multi-Method Fusion
Liu, T.-J., Lin, W., & Kuo, C.-C. J. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2012.2236343 · Cited by 195
“Examples are summarized in Table I, including MS-SSIM [3],SSIM [4], VIF [5], VSNR [6], NQM [7], PSNR-HVS [8], IFC [9], PSNR, FSIM [10], and MAD [11].”
MethodRethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff
Blau, Y., & Michaeli, T. (2019) · arXiv · doi:10.48550/arxiv.1901.07821 · Cited by 198
“Over the past decades, there has been a constant search for more “perceptual” distortion criteria, ranging from the simple SSIM/MS-SSIM (Wang et al., 2003; 2004) to the recently popular deep-feature based distortion (Johnson et al., 2016; Zhang et al., 2018).”
BackgroundMethodInfluentialA Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts
Harris, L., McRae, A. T. T., Chantry, M., Dueben, P. D., & Palmer, T. N. (2022) · Journal of Advances in Modeling Earth Systems · doi:10.1029/2022ms003120 · Cited by 198
Screen-Shooting Resilient Watermarking
Fang, H., Zhang, W., Zhou, H., Cui, H., & Yu, N. (2019) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2018.2878541 · Cited by 192
“The visual quality of the image is measured by multi-scale structural similarity (MS-SSIM) [47].”
MethodBlind Image Quality Assessment Using Statistical Structural and Luminance Features
Li, Q., Lin, W., Xu, J., & Fang, Y. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2601028 · Cited by 195
“In addition, both the statistical structural and luminance features are calculated at three scales to account for the variations of viewing distance and image resolution [9], [60].”
BackgroundNo-Reference Quality Assessment for 3D Colored Point Cloud and Mesh Models
Zhang, Z., Sun, W., Min, X., Wang, T., Lu, W., & Zhai, G. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3186894 · Cited by 190
“Supported by the vast amount of previous research on FR-IQA methods [33]– [35], many FR-MQA models have been proposed using similar manners, which usually compute local features at the vertex level and then pool the features into a quality value.”
MethodStudy of Temporal Effects on Subjective Video Quality of Experience
Bampis, C. G., Li, Z., Moorthy, A. K., Katsavounidis, I., Aaron, A., & Bovik, A. C. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2729891 · Cited by 188
“SSIM [35], MS-SSIM [36], NIQE [37], VMAF [38], ST-RRED [26] and GMSD [39].”
Self-citation
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.