Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat
Sign Up
Cited by 93Advanced Image Processing TechniquesImage and Signal Denoising MethodsImage Processing Techniques and Applications

The DOI matches its Crossref record; 3 of the 3 references it cites were found in a registry or an index.

Unified Blind Method for Multi-Image Super-Resolution and Single/Multi-Image Blur Deconvolution

Faramarzi, E., Rajan, D., Christensen, M. P.·2013·IEEE Transactions on Image Processing
DOI 10.1109/tip.2013.2237915
Open this paper in CoChat — free account

Abstract

This paper presents, for the first time, a unified blind method for multi-image super-resolution (MISR or SR), single-image blur deconvolution (SIBD), and multi-image blur deconvolution (MIBD) of low-resolution (LR) images degraded by linear space-invariant (LSI) blur, aliasing, and additive white Gaussian noise (AWGN). The proposed approach is based on alternating minimization (AM) of a new cost function with respect to the unknown high-resolution (HR) image and blurs. The regularization term for the HR image is based upon the Huber-Markov random field (HMRF) model, which is a type of variational integral that exploits the piecewise smooth nature of the HR image. The blur estimation process is supported by an edge-emphasizing smoothing operation, which improves the quality of blur estimates by enhancing strong soft edges toward step edges, while filtering out weak structures. The parameters are updated gradually so that the number of salient edges used for blur estimation increases at each iteration. For better performance, the blur estimation is done in the filter domain rather than the pixel domain, i.e., using the gradients of the LR and HR images. The regularization term for the blur is Gaussian (L2 norm), which allows for fast noniterative optimization in the frequency domain. We accelerate the processing time of SR reconstruction by separating the upsampling and registration processes from the optimization procedure. Simulation results on both synthetic and real-life i…

Overview

Integrity signals

Registry

Crossref · 10.1109/tip.2013.2237915

Cites

3 of 3 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

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?

Citations

Cites

Show all 3 references

Research works printed but not linked: 42

  1. 10.1109/CVPR.2008.4587834 · DOI
  2. 10.1109/TIP.2011.2159985 · DOI
  3. 10.1137/0917016 · DOI
  4. shewchuk, 1994, An Introduction to the Conjugate Gradient Method Without the Agonizing Pain
  5. 10.1007/978-0-85729-384-8 · DOI
  6. 10.1109/83.935034 · DOI
  7. 10.1137/0727053 · DOI
  8. 10.1016/j.imavis.2007.06.005 · DOI
  9. 10.1137/1.9780898718003 · DOI
  10. 10.1109/TIP.2011.2108306 · DOI
  11. 10.1109/CVPR.2011.5995308 · DOI
  12. 10.1145/1141911.1141956 · DOI
  13. 10.1145/1360612.1360672 · DOI
  14. 10.1145/1661412.1618491 · DOI
  15. xu, 2010, Two-phase kernel estimation for robust motion deblurring, Proc 11th Eur Conf Comput Vis I Ser, 157
  16. 10.1109/83.743855 · DOI
  17. 10.1109/TIP.2005.849322 · DOI
  18. 10.1109/TIP.2003.815260 · DOI
  19. 10.1109/ICIP.2010.5652102 · DOI
  20. xu, 2011, Image smoothing via <formula formulatype="inline"><tex Notation="TeX">$L_{0}$</tex></formula> gradient minimization, ACM Trans Graph (SIGGRAPH ASIA), 30, 174
  21. 10.1117/1.601623 · DOI
  22. 10.1093/comjnl/bxm098 · DOI
  23. 10.1016/1049-9652(91)90045-L · DOI
  24. 10.1109/TIP.2004.834669 · DOI
  25. 10.1016/j.imavis.2008.05.010 · DOI
  26. 10.1109/83.650116 · DOI
  27. 10.1109/38.988747 · DOI
  28. 10.1109/83.503915 · DOI
  29. 10.1364/COSI.2009.CTuB4 · DOI
  30. 10.1364/AO.45.002884 · DOI
  31. 10.1109/78.91207 · DOI
  32. li, 2009, Markov Random Field Modeling in Image Analysis
  33. 10.1016/S0262-8856(96)01143-2 · DOI
  34. 10.1109/83.941854 · DOI
  35. 10.1109/CVPR.1988.196317 · DOI
  36. 10.1109/83.491316 · DOI
  37. 10.1109/TIP.2009.2031231 · DOI
  38. 10.1109/83.661187 · DOI
  39. 10.1364/AO.51.000A48 · DOI
  40. 10.1109/TIP.2007.903256 · DOI
  41. 10.1109/29.9032 · DOI
  42. 10.1109/83.748894 · DOI

Cited by

Metadata

Authors
Faramarzi, E., Rajan, D., & Christensen, M. P.
Affiliations
Southern Methodist University (US)
ORCID
Venue
IEEE Transactions on Image Processing
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2013-06
Volume
22
Issue
6
Pages
2101-2114
ISSN
  • 1057-7149 (ISSN-L)
  • 1941-0042
DOI
10.1109/tip.2013.2237915
OpenAlex
W2117998419
Cited by
93
References
3
Citations by year
2026: 2 · 2025: 3 · 2024: 3 · 2023: 7 · 2022: 8 · 2021: 5 · 2020: 9 · 2019: 7 · 2018: 8 · 2017: 9 · 2016: 7 · 2015: 8 · 2014: 11 · 2013: 5
FWCI
11.62
Type
journal article
Language
en
Open access
closed
Licence
ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html (vor)
Locations
  • IEEE Transactions on Image Processing (publishedVersion)
  • PubMed (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
  • Physical Sciences › Engineering › Media Technology › Image Processing Techniques and Applications
Keywords
multi-frame super-resolution, blind image restoration, alternating optimization, image registration, computational imaging, low-resolution images
MeSH terms
Algorithms, Animals, Computer Simulation, Diagnostic Imaging, Humans, Image Processing, Computer-Assisted, Markov Chains, Photography, Phantoms, Imaging

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

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.