Unifying analysis of full reference image quality assessment
Abstract
This paper studies two increasingly popular paradigms for image quality assessment - Structural SIMilarity (SSIM) metrics and Information Fidelity metrics. The relation of the SSIM metric to Mean Squared Error and Human Visual System (HVS) based models of quality assessment are studied. The SSIM model is shown to be equivalent to models of contrast gain control of the HVS. We study the information theoretic metrics and show that the Information Fidelity Criterion (IFC) is a monotonic function of the structure term of the SSIM index applied in the sub-band filtered domain. Our analysis of the Visual Information Fidelity (VIF) criterion shows that improvements in VIF include incorporation of a contrast comparison, in addition to the structure comparison in IFC. Our analysis attempts to unify quality metrics derived from different first principles and characterize the relative performance of different QA systems.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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 spatial quality in (3) is closely related to the structure term of the SSIM index and the information theoretic basis of IQA.
“Additionally, the spatial quality in (3) is closely related to the structure term of the SSIM index and the information theoretic basis of IQA [69].”
From Motion Tuned Spatio-Temporal Quality Assessment of Natural Videos (2010) · cites this paper as [69]
In previous work, the authors established that the Gaussian Scale Mixture (GSM) image model assumption used by the information theoretic indices made them equivalent to applying the structure term of the SSIM index in a sub-band domain.
“Indeed, in previous work, we have established that the Gaussian Scale Mixture (GSM) image model assumption used by the information theoretic indices made them equivalent to applying the structure term of the SSIM index in a sub-band domain.”
From Motion Tuned Spatio-Temporal Quality Assessment of Natural Videos (2010) · cites this paper as [69]
Spatial MOVIE falls out naturally from the authors' analysis in [69] and represents an improved version of these metrics.
“Spatial MOVIE falls out naturally from our analysis in [69] and represents an improved version of these metrics.”
From Motion Tuned Spatio-Temporal Quality Assessment of Natural Videos (2010) · cites this paper as [69]
MOVIE's spatial quality model is closely related to IFC, which assumes that reference images are the output of a natural scene statistical model.
“Although our model does not explicitly assume any statistical model for the images or videos, our spatial quality model is closely related to the IFC, which assumes that the reference images are the output of a natural scene statistical model [69].”
From Motion Tuned Spatio-Temporal Quality Assessment of Natural Videos (2010) · cites this paper as [69]
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 · see citing works
Self-citationMultiscale structural similarity for image quality assessment
Wang, Z., Simoncelli, E. P., & Bovik, A. C. (2004) · The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003 · doi:10.1109/acssc.2003.1292216 · Cited by 6,253 · cited 2× · see citing works
“Our analysis supports these observations and explicitly links SSIM and contrast masking models.”
MethodSelf-citationModel of visual contrast gain control and pattern masking
Watson, A. B., & Solomon, J. A. (1997) · Journal of the Optical Society of America A · doi:10.1364/josaa.14.002379 · Cited by 472 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Blind Image Quality Assessment: From Natural Scene Statistics to Perceptual Quality
Moorthy, A. K., & Bovik, A. C. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2147325 · Cited by 1,763 · see citing works
Self-citationMotion Tuned Spatio-Temporal Quality Assessment of Natural Videos
Seshadrinathan, K., & Bovik, A. C. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2009.2034992 · Cited by 708 · see citing works
Self-citationVisual Importance Pooling for Image Quality Assessment
Moorthy, A. K., & Bovik, A. C. (2009) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2009.2015374 · Cited by 340 · see citing works
Self-citationRRED Indices: Reduced Reference Entropic Differencing for Image Quality Assessment
Soundararajan, R., & Bovik, A. C. (2012) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2166082 · Cited by 337 · see citing works
Self-citationA 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 · see citing works
Perceptually significant spatial pooling techniques for image quality assessment
Moorthy, A. K., & Bovik, A. C. (2009) · SPIE Proceedings · doi:10.1117/12.810166 · Cited by 37 · see citing works
Self-citation
- Authors
- Seshadrinathan, K., & Bovik, A. C.
- Affiliations
- The University of Texas at Austin (US)
- ORCID
- Bovik, Alan C.
- Venue
- 2008 15th IEEE International Conference on Image Processing
- Publisher
- IEEE
- Published
- 2008
- Pages
- 1200-1203
- ISSN
- 1522-4880 (ISSN-L)
- OpenAlex
- W2135377272
- Cited by
- 85
- References
- 3
- Citations by year
- 2025: 3 · 2024: 2 · 2023: 2 · 2022: 4 · 2021: 3 · 2020: 3 · 2019: 1 · 2018: 2 · 2017: 4 · 2016: 2 · 2015: 8 · 2014: 2 · 2013: 8 · 2012: 7
- FWCI
- 9.08
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Proceedings - International Conference on Image Processing (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
- full-reference image quality assessment, structural similarity index, visual information fidelity, mean squared error, human visual system, contrast gain control, subband filtering, structural similarity
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.
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
