Name
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. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/ICCV.2011.6126278 | ICCV |
Keywords | Field | DocType |
image processing application,natural image patch,good image prior,high likelihood,patch model,full image,natural image,better patch prior,whole image restoration,image denoising,whole image,patch restoration,noise reduction,image reconstruction,cost function,gaussian mixture model,image restoration,gaussian processes,mathematical model,computer vision,noise measurement,maximum likelihood estimation,estimation | Iterative reconstruction,Computer vision,Deblurring,Pattern recognition,Computer science,Inpainting,Gaussian,Gaussian process,Artificial intelligence,Image restoration,Prior probability,Mixture model | Conference |
Volume | Issue | ISSN |
2011 | 1 | 1550-5499 |
Citations | PageRank | References |
357 | 9.82 | 14 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Daniel Zoran | 1 | 357 | 9.82 |
| Yair Weiss | 2 | 10240 | 834.60 |