Variational Bayesian Blind Deconvolution Using a Total Variation Prior

被引:175
作者
Babacan, S. Derin [1 ]
Molina, Rafael [2 ]
Katsaggelos, Aggelos K. [1 ]
机构
[1] Northwestern Univ, Dept Elect Engn & Comp Sci, Evanston, IL 60208 USA
[2] Univ Granada, Dept Ciencias Computac & IA, E-18071 Granada, Spain
关键词
Bayesian methods; blind deconvolution; parameter estimation; total variation (TV); variational methods; IMAGE-RESTORATION;
D O I
10.1109/TIP.2008.2007354
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we present novel algorithms for total variation (TV) based blind deconvolution and parameter estimation utilizing a variational framework. Using a hierarchical Bayesian model, the unknown image, blur, and hyperparameters for the image, blur, and noise priors are estimated simultaneously. A variational inference approach is utilized so that approximations of the posterior distributions of the unknowns are obtained, thus providing a measure of the uncertainty of the estimates. Experimental results demonstrate that the proposed approaches provide higher restoration performance than non-TV-based methods without any assumptions about the unknown hyperparameters.
引用
收藏
页码:12 / 26
页数:15
相关论文
共 39 条
[1]  
ADAMI KZ, PHYSTAT
[2]  
ALMEIDA MSC, 2008, ICASSP LAS VEG NV AP
[3]   IMAGE-RESTORATION BASED ON A SUBJECTIVE CRITERION [J].
ANDERSON, GL ;
NETRAVALI, AN .
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1976, 6 (12) :845-853
[4]   Parameter estimation in TV image restoration using variational distribution approximation [J].
Babacan, S. Derin ;
Molina, Rafael ;
Katsaggelos, Aggelos K. .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2008, 17 (03) :326-339
[5]  
BABACAN SD, 2007, EUSIPCO POZN POL SEP
[6]  
BABACAN SD, 2007, INT C IM PROC SAN AN
[7]  
Bar L, 2004, LECT NOTES COMPUT SC, V3022, P166
[8]  
BEAL M, 2003, THESIS GATSBY COMPUT
[9]  
BERGER JO, 1985, STAT DECISION THEORY, pCH3
[10]  
Bernardo J. M., 1994, Bayesian theory, DOI 10.1002/9780470316870