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 5,801–5,900 of 6,047
Color harmony : experimental and computational modeling
Chamaret, C. (2016) · theses.fr (ABES) · doi:10.70675/c59759aez7b7ez498cz8278z2398c346b854 · Cited by 7
Contributions to objective and subjective visual quality assessment of 3d models
Guo, J. (2016) · theses.fr (ABES) · doi:10.70675/24fc673fz0af9z4c2fz905fzbd37270eead1 · Cited by 1
“Improved metrics: MS-SSIM (Multi-scale structural similarity) [129] and IW-SSIM (Information content weighting structural similarity) [128] were therefore designed for resolving the problems.”
BackgroundMethodInfluentialPredicting home Wi-Fi QoE from passive measurements on commodity access points
da Hora, D. N. (2017) · theses.fr (ABES) · doi:10.70675/aa409061zc102z4b2fz839az3f6446c90101
“We use support vector regression (SVR) to train predictors, and show that Tx PHY rate, frame delivery ratio, and counters of Wi-Fi and non Wi-Fi occupation can predict estimated degradation mean opinion scores (DMOS, in range [1-5]) with root mean square errors between 0.643 and 0.777.”
BackgroundInfluentialAkbari, A. (2018) · theses.fr (ABES) · doi:10.70675/9c066927ze707z40c7zb2bfz65a4797f304c
“In terms of PSNR and MSSIM, the performance of the proposed JSR-based EC algorithm is better than most of the competing methods, especially in the consecutive and random loss patterns.”
MethodInfluentialQuality assessment of stereoscopic 3D content based on binocular perception
Fan, Y. (2019) · theses.fr (ABES) · doi:10.70675/c06f8c6fzd28bz433cza7e2z03f88a6cb9cb
Masque psychovisuel à base d’ondelettes pour le Watermarking
Amar, M. (2018) · theses.fr (ABES) · doi:10.70675/97d28861zbd9ez4d6az81cfz79ac15f98679
Tsukanova, A. (2019) · theses.fr (ABES) · doi:10.70675/1cc931a0z724ez4285z85d2z7dd4bd0e2456
Morozkin, P. (2018) · theses.fr (ABES) · doi:10.70675/802f16c2z0e69z48c5zac3dzf92ecef1fe73 · Cited by 1
Tatouage des images médicales partagées
Karasad, M. (2018) · theses.fr (ABES) · doi:10.70675/42584764za3fez47ebzb908z2669f5116d39
Image quality assessment of High Dynamic Range and Wide Color Gamut images
Rousselot, M. (2019) · theses.fr (ABES) · doi:10.70675/3a128c55zdb77z4a2ezb292z396a7f8ee630 · Cited by 2
“Benchmark of existing HDR objective quality metrics VDP-2 is always in the first or second best performing metric except for the database Korshunov et al. but in this case, the difference between HDR-VDP-2 SROCC and the best metric SROCC (PU-MS-SSIM) is inferior at 0.01 which is not significant.”
BackgroundMethodInfluentialImage Quality Assessment of 3D Synthesized Views
Tian, S. (2019) · theses.fr (ABES) · doi:10.70675/e9dda12ezf7d2z4b92zbc45zc4a92e6f9657 · Cited by 1
Survivre à la prolifération massive des malwares sur mobile
Gitzinger, L. (2020) · theses.fr (ABES) · doi:10.70675/e8e9f1efz3c34z4da9z9147zd2836718a9ea · Cited by 1
Design of learned video coding schemes
Ladune, T. (2021) · theses.fr (ABES) · doi:10.70675/45608d60z49c5z44faz8766z655c4cccc4d6 · Cited by 3
Ak, A. (2022) · theses.fr (ABES) · doi:10.70675/c96975f8z9224z40f9zb988zb6b4c7af5c5b · Cited by 1
Khan, Z. A. (2021) · theses.fr (ABES) · doi:10.70675/75d15fa7z97c5z418cza3b3z8f75630fddaa · Cited by 2
Content-aware HDR tone mapping algorithms
Goswami, A. (2022) · theses.fr (ABES) · doi:10.70675/886fdc43z0105z4a39z9b47zfcc9ed5cb5ab
Joint Degradation-Aware Arbitrary-Scale Super-Resolution for Variable-Rate Extreme Image Compression
Chai, X., Cheng, Z., Li, X., et al. (2026) · IEEE Transactions on Broadcasting · doi:10.1109/tbc.2026.3680050
“To comprehensively assess both fidelity and perceptual quality, we report a set of commonly used metrics, including MS-SSIM [83], LPIPS [84], DISTS [85], CLIPScore d clip [86], and FID [87].”
Xie, X., Wang, Q., Liu, Y., et al. (2026) · Journal of the Society for Information Display · doi:10.1002/jsid.70066
Leveraging Diffusion-Based Augmentation for Robust Semantic Segmentation
Salman, M. M., Gerhardt, C., & Broll, W. (2025) · International Conference on Machine Learning and Applications · doi:10.1109/icmla66185.2025.00154
“• We conduct comprehensive qualitative and quantitative evaluations using FID [12], LPIPS [31], MS-SSIM [25], and mIoU consistency to compare fidelity and semantic preservation across the three pipelines.”
Learning based coding and post-processing methods for 8K video reconstruction
Bonnineau, C. (2022) · theses.fr (ABES) · doi:10.70675/1549af8az0a5bz4d20z89b5z7dfee3385006
Visual quality of rendered 3D meshes with color attributes : Subjective and objective evaluation
Nehmé, Y. (2021) · theses.fr (ABES) · doi:10.70675/d7b16080za911z400dz9b22z099d29a5e415
Spectral and Spatial Graph Learning for Multispectral Solar Image Compression
Siwakoti, P., Khoshkhahtinat, A., Mehta, P. M., et al. (2025) · International Conference on Machine Learning and Applications · doi:10.1109/icmla66185.2025.00089
“We preprocess each input image by applying a logarithmic transformation to compress the dynamic range, followed by normalization and random cropping into 256 × 256 patches.”
GAN-based face image synthesis and its application to face recognition
Yin, X. (2022) · theses.fr (ABES) · doi:10.70675/6aef4315za3fbz4be8zab59z6f74668ca8fb
Deep learning for embedded image compression in Earth Observation
de Oliveira, V. A. (2022) · theses.fr (ABES) · doi:10.70675/f9a47da0z6a4fz40eaz805ez33287fd80bc5
Image Compression-Encryption Algorithm Using Huffman Coding and AES
Farajallah, M., Isayed, S., Tamimi, L., & Amar, I. (2026) · AI Computer Science and Robotics Technology · doi:10.5772/acrt20250107
Generative models for complex visual content
Careil, M. (2024) · theses.fr (ABES) · doi:10.70675/71c84118z5b99z48a2za601zc5fb1c90b2b9
Low Bitrate Face Video Compression with Generative Animation Models
Konuko, G. (2025) · theses.fr (ABES) · doi:10.70675/478ecc9az4adez4d1dzb4c7z37d2f6f05ac5
Deep learning-assisted video list decoding in error-prone video transmission systems
Zhang, Y. (2024) · theses.fr (ABES) · doi:10.70675/1d0878eez4905z432az9623zbee74e1a454f
Towards practical end-to-end learned video coding
Tarchouli, M. (2024) · theses.fr (ABES) · doi:10.70675/be5b3270ze870z4309zba4fz80382c25ab7f
Exploration of Lossy Image Coding Trade-off between Rate, Machine Perception and Quality
Marie, A. (2023) · theses.fr (ABES) · doi:10.70675/1303cd1eze77az4057zadb2z2b818272ba1a
Machine Learning-based Depth Estimation and View Synthesis for Immersive Video
Ravi, S. L. (2023) · theses.fr (ABES) · doi:10.70675/4262b4b2z7a3dz41f7zb3ddz125823bdae72
Semantic compression of large image collection
Bachard, T. (2024) · theses.fr (ABES) · doi:10.70675/21be00c2z53d7z46b1z8f63z92754885f018
Improving image quality using high dynamic range and aesthetics assessment
Chambe, M. (2023) · theses.fr (ABES) · doi:10.70675/9f28e6f3z7eb3z414cz9752z1b2c8e4a8c95
On depth prediction for autonomous driving using self-supervised learning
Boulahbal, H. E. (2023) · theses.fr (ABES) · doi:10.70675/273dde48zd8b7z42b8z9c85z52bfc7aa4bba
Wang, M., Shang, B., Yao, J., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6543202
Deep Optical Cryptography: Joint Encryption and LC Lens Key Generation for Secure Displays
Chen, T.-Y., Wu, J.-L., Tung, S., et al. (2026) · Journal of the Society for Information Display · doi:10.1002/jsid.70075
“In parallel, we use the multiscale structural similarity (MS-SSIM) index to assess perceptual reconstruction fidelity be-tween the decrypted image and the plaintext and to quantify residual structural similarity between the ciphertext and the plaintext [12].”
G2-SDF: Geometry-Guided Neural Signed Distance Field for Space Target Reconstruction
Tang, P., Li, Z. J., Chen, Y., et al. (2026) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2026.3685232
“Furthermore, θ isoptimizedusing L 1lossandmultiscale structural similarity index measure (MS-SSIM) loss [32], [33], which are written as follows: L MS_ r ( θ ) = 1 − ms_ssim I r , I gt (17) where I gt is the ground truth, (cid:7) · (cid:7) 1 denotes the one norm; μ x and μ y are the means, σ x 2…”
Chen, Z., Liu, J., Zhang, R., Li, C., Cao, D., & Zhang, Y. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463417
HM-Avatar: Towards Realistic Loose Garment Modeling With Hierarchical MLPs
Wang, H., Deng, Z., Chen, X., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462401
A Hybrid Grid-Based Method for Video Representation
Zhao, M., Liu, M., Huang, W., et al. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463942
Attribute Driven W Space for Query Limited Face Template Inversion
Zhou, Z.-H., Shen, Z.-X., Dai, L., et al. (2026) · IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp55912.2026.11464720
Occlusion-Robust Human Rendering Based on Tri-Plane Restoration
Wang, S.-P., Shao, H.-C., & LIN, C. A. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462040
SCENE: Semantic-Aware Codec Enhancement with Neural Embeddings
Lin, H.-Y., Chen, L.-W., & Lee, H.-S. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460563
MAGF-UIENet: A Multiscale Attention Guided Fusion Network for Underwater Image Enhancement
Zhao, C., & Chen, X. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462337
TRJSCC: Text-Guided ROI-Aware Deep Joint Source-Channel Coding
Fan, R., Ma, S., Xie, X., & Shi, G. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462189
Rate-Distortion Analysis of Optically Passive Vision Compression
Ogden, R. R., Fridovich-Keil, D., & Tanaka, T. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11465024
CP Loss: Channel-Wise Perceptual Loss for Time Series Forecasting
Zha, Y., Fan, C., Liu, P., Jiang, Y., Dai, T., Hai, W., & Xia, S. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461400
Blind Quality Assessment of Stereoscopic Videos Using Scene-Based Attributes
Ryakala, S. K., Mogasati, R. S., & Appina, B. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11464202
BTRFusion: Misaligned Medical Image Fusion via Bidirectional Translation and Registration
Chang, Y., & Li, Z. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11460786
A Channel Adaptive Encoding and Decoding Method for Unmanned Aerial Vehicle Image Transmission
Zhang, Z., Zhang, S., Qiu, Q., Li, B., Zhang, C., & Shi, G. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3686205
“In this study, to evaluate the quality of the received images, we use three evaluation metrics: PSNR, the perceptual metric MS-SSIM [73], LPIPS [74], and classification accuracy.”
MSDS: Deep Structural Similarity With Multiscale Representation
Kang, D., Chen, X.-H., Liu, B., Zhang, K., Chen, W., & Zhao, T. (2026) · IEEE Signal Processing Letters · doi:10.1109/lsp.2026.3726843
“While multiscale modeling has been extensively studied in traditional IQA, such as MS-SSIM [2], its role in deep-feature-based similarity remains insufficiently explored.”
Perceptual Learning for On-Line Visual Object Tracking
Cicco, D. D., Iannuzzo, G., Nardo, E. D., & Ciaramella, A. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-981-95-4072-3_32
Skin Tone Transfer in the Wild: A Comprehensive Comparison of Colour Transfer Approaches
Wu, B., Tokas, M., & Jung, U. (2026) · IET Image Processing · doi:10.1049/ipr2.70374
Advances in Neural 3D Mesh Texturing: A Survey
Perla, S. R. K., Zhang, H., & Amiri, A. M. (2026) · Computer Graphics Forum · doi:10.1111/cgf.70392 · Cited by 1
“Peak Signal-to-Noise Ratio (PSNR; ↑ ) [ZIE ∗ 18] and the Structural Similarity Index (SSIM; ↑ ) [WBSS04,WSB03] are frequently reported to quantify low-level fidelity—higher PSNR or SSIM on rendered views indicates that the synthesized texture preserves more detail and structure from the ground…”
Choi, B. (2026) · American Journal of Art and Design · doi:10.11648/j.ajad.20261102.11
Yan, Q., Sun, G., Liu, C., Ma, J., Zheng, Y., Jiang, Z., Xia, T., & Wang, Q. J. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.110414
Marulli, M., & Bertini, M. (2026) · IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv61042.2026.00821
From Prompt to Production: Automating Brand-Safe Marketing Imagery with Text-to-Image Models
Atighehchian, P., Wang, H., Kapustin, A., Lerner, B., Jiang, T., Jensen, T., & Sokhandan, N. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00659
“We use the following metrics to evaluate performance across the three key axes: • Product Fidelity : We use DINOv2 [7] features and MS-SSIM [17] to evaluate how well the original product is preserved in the generated image.”
Rethinking Latent Variable in Learned Image Compression
Yi, F., Gong, Z., & Zeng, H. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00823 · Cited by 2
“1 has achieved huge progress in rate-distortion performance on metrics of Signal-to-Noise Ratio (PSNR) and Multi-Scale-Structural Similarity Index Measure (MS-SSIM) [35].”
Line Art Colorization with Offset Prior-based Diffusion Model
Zhu, X., Cao, M., Zhang, F., Lai, Y., & Rosin, P. L. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00540
“For performance evaluation, we use Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM) [44], Quaternion Structural Similarity (QSSIM) [19], Multi-scale SSIM (MS-SSIM) [43], and FID [12] to assess the quality of the generated results.”
A Framework for 3D Forest Map Reconstruction Based on Gaussian Splatting
Phan, D.-D., Trinh, T.-T., Trinh, M.-L., et al. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-14935-0_13
Hossain, M., Tamjid, A. J., Hussain, M. I., et al. (2025) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit68739.2025.11491192
“SSIM quantifies structural similarity; greater values reflect better fidelity [17]: where µ , σ 2 , and σ xy denote means, variances, and covariance; C 1 , C 2 stabilize the division.”
Multi-scale Feature Fusion Based Learning for Image Compression
Yang, Y., & Wang, K. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-8660-8_28
Ding, Z., Ding, Z., Men, Y., Liu, Y., Luan, S., & Tian, S. (2026) · Applied Intelligence · doi:10.1007/s10489-026-07252-8
“…the fused image O F preserves the structural information present in the pseudo-labels, we employ the multi-scale structural similarity (MS-SSIM) [32] metric: (15) This term penalizes structural dissimilarity between the fused image and each pseudo-label, encouraging the network to learn the…”
STAC: A Spatio-Temporal Transformer with Adaptive Context for Video Compression
Sandaruwan, R., & Fernando, A. (2026) · Applied Sciences · doi:10.3390/app16094568 · Cited by 1
VI-HAPFNet: Haze-aware prompt fusion network for visible-infrared image dehazing
Xiao, W., Zhang, J., Liu, M., Bi, J., Guo, Y., & Pan, C. (2026) · The Visual Computer · doi:10.1007/s00371-026-04512-z
Chen, E., Tian, Y., Deng, X. F., et al. (2026) · AIAA Journal · doi:10.2514/1.j066886
Video Quality Evaluation Methodology and Result of AV2 Compression Performance
Lei, Z., Vibhoothi, V., Hoang, D., Du, Y., & Khsib, R. (2026) · Proceedings - International Conference on Image Processing · doi:10.1109/icip61757.2026.11630420
Film and Television Image Clarity Analysis Based on Objective Image Quality Assessment Metrics
Tang, M. (2026) · Textile & Leather Review · doi:10.31881/tlr.2026.1867
CSEval: A Framework for Evaluating Clinical Semantics in Text-to-Image Generation
Cronshaw, R., Vilouras, K., Yan, J., Du, Y., Chen, F., McDonagh, S., & Tsaftaris, S. A. (2026) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi61048.2026.11516022
Li, H., Dragonu, I., Jezzard, P., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.05.18.725892
“All models were pre-trained for 50 epochs using the Adam optimizer with a learning rate of 3 × 10⁻⁴, batch size of 3, and validation-based early stopping, minimizing the proposed histogram-weighted L1+SSIM loss.”
InfluentialHu, Y., Wang, Y., Rodríguez, N. E. Q., Yang, R., Hsu, W.-C., Luo, S., Bai, Z., Wu, J., Dai, Y., Wu, S., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38236-8_48
Gaussian Wardrobe: Compositional 3D Gaussian Avatars for Free-Form Virtual Try-On
Chen, Z., Song, J., Ho, H.-I., Kaufmann, M., Jiang, T., & Guo, C. (2026) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv69130.2026.00076
“As the source code for LayGA is not public, we re-implemented the method based on direct guidance from the original authors to ensure fidelity.”
Time-Evidence Dual Gating for Blue-and-White Porcelain Style Transfer
徐, 子. (2026) · Modeling and Simulation · doi:10.12677/mos.2026.155084
Single-number reference infrared image quality assessment via graph convolutional networks
Gao, Y., Hu, B., & Chen, Z. (2026) · Displays · doi:10.1016/j.displa.2026.103553
Machine learning workflows in climate modelling: design patterns and insights from case studies
Zheng, T., Venkatasubramanian, S., Li, S. S., Braverman, A., Ke, X., Hou, Z., Jin, P., & Agrawal, S. (2026) · Philosophical Transactions of the Royal Society A Mathematical Physical and Engineering Sciences · doi:10.1098/rsta.2025.0254 · Cited by 1
End-to-End Spectrally Driven Colorimetric Calibration Framework for Color Imaging Systems
Zhai, J., Wang, H., Zeng, M., et al. (2026) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2026.3698408 · Cited by 1
“…conversion and the actual images, this study introduced additional metrics, including the SSIM [36], Multi-Scale Structural Similarity (MS-SSIM) [37], Learned Perceptual Image Similarity (LPIPS), and Fréchet Inception Distance (FID) [38], to evaluate the visual differences between predicted and…”
Xiao, S., Yu, S., & Lin, X. (2026) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2026.2679731
Introduction of Semantic Communication
Chen, W., & Qin, Z. (2026) · Textbooks in telecommunication engineering · doi:10.1007/978-3-032-11005-3_2
Wei, F., Huang, H., Sun, W., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6864569
ResiGuide: Residual-Guided Hierarchical Entropy Modeling for Edge–IoT Devices
Ding, Y., Chen, Z. Q., & Wei, J. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3698390
“Following the common practice in LIC and the standard configuration in CompressAI [37], we train ten models optimized for mse and MS structural similarity (MS-SSIM) [38], respectively.”
Dynamical System Approach to Linear Inverse Problems Using Mutual Power Divergence
Kasai, R., Al-Ola, O. M. A., Kojima, T., et al. (2026) · Mathematics · doi:10.3390/math14111912
Distributed Deep Joint Source-Channel Coding of Videos in Autonomous Aerial Vehicle Networks
Zhang, Z., Yang, Q., Duan, Y., et al. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3700200
“The bandwidth compression ratio, denoted by ρ , is given by: To evaluate video reconstruction quality at the receiver, we adopt two widely used distortion metrics: the Peak Signal-to-Noise Ratio (PSNR) and the Multi-Scale Structural Similarity Index Measure (MS-SSIM) [43].”
Seismic Data Interpolation Using Task‐Driven Pixel‐Level Masked Autoencoders
Liu, N., Liu, K., Hua, G., et al. (2026) · Geophysical Prospecting · doi:10.1111/1365-2478.70200
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.