Learning to Deblur
Abstract
We describe a learning-based approach to blind image deconvolution. It uses a deep layered architecture, parts of which are borrowed from recent work on neural network learning, and parts of which incorporate computations that are specific to image deconvolution. The system is trained end-to-end on a set of artificially generated training examples, enabling competitive performance in blind deconvolution, both with respect to quality and runtime.
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?
Several neural network supported methods are utilized in literature.
“Several neural networks supported methods are utilized in literature, such as by Schuler et al. [15].”
From A Comprehensive Review of Blind Deconvolution Techniques for Image Deblurring (2020) · cites this paper as [15]
The MAP estimation for deconvolution was previously presumed to derive only a trivial delta kernel solution, but recent improvements have shown that MAP can derive effective results even for a non-trivial blur kernel.
“The MAP estimation for deconvolution was previously presumed to derive a trivial delta kernel solution only, but recent improvements have shown that the MAP method of estimation can derive effective results even for a non-trivial blur kernel [15, 24, 25] etc.”
From A Comprehensive Review of Blind Deconvolution Techniques for Image Deblurring (2020) · cites this paper as [15]
The Lp norm (0 ≤ p ≤ 1) is most effective in the range p =0.3, 0.5-0.8.
“Most effective in the range p =0.3, 0.5-0.8”
From A Comprehensive Review of Blind Deconvolution Techniques for Image Deblurring (2020) · cites this paper as [15]
Learned priors or Trained priors lead effective recovery of the Blur Kernel.
“Lead effective recovery of the Blur Kernel”
From A Comprehensive Review of Blind Deconvolution Techniques for Image Deblurring (2020) · cites this paper as [15]
Cites
Gaussian Processes for Machine Learning
Rasmussen, C. E., & Williams, C. K. I. (2005) · doi:10.7551/mitpress/3206.001.0001 · Cited by 11,705 · see citing works
ADADELTA: An Adaptive Learning Rate Method
Zeiler, M. D. (2012) · arXiv · doi:10.48550/arxiv.1212.5701 · Cited by 5,322 · see citing works
A Machine Learning Approach for Non-blind Image Deconvolution
Schuler, C. J., Burger, H. C., Harmeling, S., & Scholkopf, B. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.142 · Cited by 319 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Artificial intelligence in the creative industries: a review
Anantrasirichai, N., & Bull, D. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10039-7 · Cited by 793 · see citing works
All in One Bad Weather Removal Using Architectural Search
Li, R., Tan, R. T., & Cheong, L.-F. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00324 · Cited by 377 · see citing works
A Comprehensive Review of Blind Deconvolution Techniques for Image Deblurring
Satish, P., Srikantaswamy, M., & Ramaswamy, N. (2020) · Traitement du signal · doi:10.18280/ts.370321 · Cited by 59 · see citing works
- Authors
- Schuler, C. J., Hirsch, M., Harmeling, S., & Schölkopf, B.
- Affiliations
- MPI for Intelligent Systems, Spemannstr. 38, Tuebingen, Germany
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2016-07-01
- Volume
- 38
- Issue
- 7
- Pages
- 1439-1451
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W1457323852
- Cited by
- 560
- References
- 3
- Citations by year
- 2026: 11 · 2025: 37 · 2024: 56 · 2023: 69 · 2022: 69 · 2021: 68 · 2020: 89 · 2019: 65 · 2018: 48 · 2017: 34 · 2016: 9 · 2015: 5
- FWCI
- 27.72
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques
- Physical Sciences › Engineering › Media Technology › Image Processing Techniques and Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Keywords
- blind image deconvolution, image deblurring, deep neural network, end-to-end learning, synthetic training data, image restoration
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
