From learning models of natural image patches to whole image restoration

Daniel Zoran*, Yair Weiss

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1252 Scopus citations

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.

Original languageAmerican English
Title of host publication2011 International Conference on Computer Vision, ICCV 2011
Pages479-486
Number of pages8
DOIs
StatePublished - 2011
Event2011 IEEE International Conference on Computer Vision, ICCV 2011 - Barcelona, Spain
Duration: 6 Nov 201113 Nov 2011

Publication series

NameProceedings of the IEEE International Conference on Computer Vision

Conference

Conference2011 IEEE International Conference on Computer Vision, ICCV 2011
Country/TerritorySpain
CityBarcelona
Period6/11/1113/11/11

Fingerprint

Dive into the research topics of 'From learning models of natural image patches to whole image restoration'. Together they form a unique fingerprint.

Cite this