Name
Abstract | ||
|---|---|---|
The restoration of a blurry or noisy image is commonly performed with a MAP estimator, which maximizes a posterior probability to reconstruct a clean image from a degraded image. A MAP estimator, when used with a sparse gradient image prior, reconstructs piecewise smooth images and typically removes textures that are important for visual realism. We present an alternative deconvolution method called iterative distribution reweighting (IDR) which imposes a global constraint on gradients so that a reconstructed image should have a gradient distribution similar to a reference distribution. In natural images, a reference distribution not only varies from one image to another, but also within an image depending on texture. We estimate a reference distribution directly from an input image for each texture segment. Our algorithm is able to restore rich mid-frequency textures. A large-scale user study supports the conclusion that our algorithm improves the visual realism of reconstructed images compared to those of MAP estimators. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/TPAMI.2011.166 | IEEE transactions on pattern analysis and machine intelligence |
Keywords | Field | DocType |
degraded image,iterative distribution reweighting method,blurry image,map estimator,maximum likelihood estimation,posterior probability,piecewise smooth image,maximum a priori estimator,image restoration,nonblind deconvolution,deconvolution,visual realism,input image,noisy image,clean image,reconstructed image,sparse gradient image prior,smooth image,image deblurring,image prior,matching gradient distributions,reference distribution,image texture,gradient distribution matching,image denoising.,deconvolution method,iterative methods,natural image,noise,gaussian distribution,kernel,image reconstruction,cost function,algorithms | Iterative reconstruction,Computer vision,Image gradient,Pattern recognition,Feature detection (computer vision),Image texture,Computer science,Deconvolution,Posterior probability,Artificial intelligence,Image restoration,Estimator | Journal |
Volume | Issue | ISSN |
34 | 4 | 0162-8828 |
Citations | PageRank | References |
21 | 0.81 | 27 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Taeg Sang Cho | 1 | 215 | 12.62 |
| C. Lawrence Zitnick | 2 | 7321 | 332.72 |
| Neel Joshi | 3 | 1155 | 63.95 |
| Sing Bing Kang | 4 | 5064 | 345.13 |
| Richard Szeliski | 5 | 21300 | 2104.74 |
| William T. Freeman | 6 | 17382 | 1968.76 |