From learning models of natural image patches to whole image restoration
The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
Learning good image priors is of utmost importance for the study of vision, computer vision and image processing applications. Learning priors and optimizing over whole images can lead to tremendous computational challenges. In contrast, when we work with small image patches, it is possible to learn priors and perform patch restoration very efficiently. This raises three questions - do priors that give high likelihood to the data also lead to good performance in restoration? Can we use such patch based priors to restore a full image? Can we learn better patch priors? In this work we answer these questions. We compare the likelihood of several patch models and show that priors that give high likelihood to data perform better in patch restoration. Motivated by this result, we propose a generic framework which allows for whole image restoration using any patch based prior for which a MAP (or approximate MAP) estimate can be calculated. We show how to derive an appropriate cost function, how to optimize it and how to use it to restore whole images. Finally, we present a generic, surprisingly simple Gaussian Mixture prior, learned from a set of natural images. When used with the proposed framework, this Gaussian Mixture Model outperforms all other generic prior methods for image denoising, deblurring and inpainting.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Martin, D., Fowlkes, C., Tal, D., & Malik, J. (2002) · Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 · doi:10.1109/iccv.2001.937655 · Cited by 8,216 · cited 5×
“We compare the log likelihood each model gives on a set of unseen natural image patches (sampled from the test set of [10]) and the performance of each model in patch denoising using MAP estimates.”
BackgroundMethodInfluentialA Non-Local Algorithm for Image Denoising
Buades, A., Coll, B., & Morel, J.-M. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.38 · Cited by 7,616 · cited 2×
“Good priors have been applied to different tasks such as image denoising [1, 2, 3, 4, 5, 6], image inpainting [6] and more [7], yielding excellent results.”
BackgroundMethodImage Denoising Via Sparse and Redundant Representations Over Learned Dictionaries
Elad, M., & Aharon, M. (2006) · IEEE Transactions on Image Processing · doi:10.1109/tip.2006.881969 · Cited by 5,321
Image denoising using scale mixtures of gaussians in the wavelet domain
Portilla, J., Strela, V., Wainwright, M. J., & Simoncelli, E. P. (2003) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.818640 · Cited by 2,255
Non-local sparse models for image restoration
Mairal, J., Bach, F., Ponce, J., Sapiro, G., & Zisserman, A. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459452 · Cited by 1,666
Fast Image Deconvolution using Hyper-Laplacian Priors
Krishnan, D., & Fergus, R. (2009) · neural information processing systems · Cited by 1,470
Nonlinear image recovery with half-quadratic regularization
Geman, D., & Yang, C. (1995) · IEEE Transactions on Image Processing · doi:10.1109/83.392335 · Cited by 1,000 · cited 1×
“alternative optimization method called “Half Quadratic Splitting” which has been proposed recently in several relevant contexts [11, 7].”
MethodRoth, S., & Black, M. J. (2009) · International Journal of Computer Vision · doi:10.1007/s11263-008-0197-6 · Cited by 847
Yu, G.-S., Sapiro, G., & Mallat, S. (2010) · IEEE Transactions on Image Processing · doi:10.21236/ada540722 · Cited by 625
Lindsay, B. G. (1988) · Contemporary Mathematics · doi:10.1090/conm/080/999014 · Cited by 553
Image restoration by sparse 3D transform-domain collaborative filtering
Dabov, K., Foi, A., Katkovnik, V., & Egiazarian, K. (2008) · SPIE Proceedings · doi:10.1117/12.766355 · Cited by 461
Joe, H., Reid, N. M., Xuekun, P., & Firth, D. (2012) · Cited by 434
What makes a good model of natural images?
Weiss, Y., & Freeman, W. T. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.383092 · Cited by 300
Self-citationScale invariance and noise in natural images
Zoran, D., & Weiss, Y. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459476 · Cited by 238
Self-citationMode-finding for mixtures of Gaussian distributions
Carreira-Perpinan, M. A. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.888716 · Cited by 192
A Discriminative Approach for Wavelet Denoising
Hel-Or, Y., & Shaked, D. (2008) · IEEE Transactions on Image Processing · doi:10.1109/tip.2008.917204 · Cited by 64
Who killed the directed model?
Domke, J., Karapurkar, A., & Aloimonos, Y. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587817 · Cited by 25
Cited by
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
Zhang, K., Zuo, W., Chen, Y., Meng, D., & Zhang, L. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2662206 · Cited by 8,983
“It can be seen that the effective patch size used in EPLL [33] is the smallest, i.e., 36 × 36 .”
MethodFFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising
Zhang, K., Zuo, W., & Zhang, L. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2839891 · Cited by 2,678
Weighted Nuclear Norm Minimization with Application to Image Denoising
Gu, S., Zhang, L., Zuo, W., & Feng, X. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.366 · Cited by 2,316
Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
Nah, S., Kim, T. H., & Lee, K. M. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.35 · Cited by 2,275
Learning Deep CNN Denoiser Prior for Image Restoration
Zhang, K., Zuo, W., Gu, S., & Zhang, L. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.300 · Cited by 2,116
Metadata
- Authors
- Zoran, D., & Weiss, Y.
- Affiliations
- Hebrew University of Jerusalem (IL)
- ORCID
- Zoran, Daniel
- Venue
- 2011 International Conference on Computer Vision
- Publisher
- IEEE
- Published
- 2011-11
- Pages
- 479-486
- OpenAlex
- W2172275395
- Cited by
- 1,522
- References
- 17
- Citations by year
- 2026: 23 · 2025: 53 · 2024: 94 · 2023: 122 · 2022: 130 · 2021: 165 · 2020: 177 · 2019: 171 · 2018: 158 · 2017: 128 · 2016: 112 · 2015: 77 · 2014: 52 · 2013: 45 · 2012: 15
- FWCI
- 26.66
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Keywords
- image priors, natural image patches, maximum a posteriori estimation, Gaussian mixture model, image denoising, image deblurring, image inpainting
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.