Variational Bayesian compressive blind image deconvolution. Amizic, B., Spinoulas, L., Molina, R., & Katsaggelos, A. K. In European Signal Processing Conference, pages 1–5, 2013. IEEE. abstract bibtex We propose a novel variational Bayesian framework to perform simultaneous compressive sensing (CS) image reconstruction and blind deconvolution (BID) as well as estimate all modeling parameters. Furthermore, we show that the proposed framework generalizes the alternating direction method of multipliers which is often utilized to transform a constrained optimization problem into an unconstrained one through the use of the augmented Lagrangian. The proposed framework can be easily adapted to other signal processing applications or particular image and blur priors within the proposed context. In this work, as an example, we employ the following priors to illustrate the significance of the proposed approach: (1) a non-convex lp quasi-norm based prior for the image, (2) a simultaneous auto-regressive prior for the blur, and (3) an l1 norm based prior for the transformed coefficients. Experimental results using synthetic images demonstrate the advantages of the proposed algorithm over existing approaches. © 2013 EURASIP.
@inproceedings{amizic2013variational,
abstract = {We propose a novel variational Bayesian framework to perform simultaneous compressive sensing (CS) image reconstruction and blind deconvolution (BID) as well as estimate all modeling parameters. Furthermore, we show that the proposed framework generalizes the alternating direction method of multipliers which is often utilized to transform a constrained optimization problem into an unconstrained one through the use of the augmented Lagrangian. The proposed framework can be easily adapted to other signal processing applications or particular image and blur priors within the proposed context. In this work, as an example, we employ the following priors to illustrate the significance of the proposed approach: (1) a non-convex lp quasi-norm based prior for the image, (2) a simultaneous auto-regressive prior for the blur, and (3) an l1 norm based prior for the transformed coefficients. Experimental results using synthetic images demonstrate the advantages of the proposed algorithm over existing approaches. {\textcopyright} 2013 EURASIP.},
author = {Amizic, Bruno and Spinoulas, Leonidas and Molina, Rafael and Katsaggelos, Aggelos K.},
booktitle = {European Signal Processing Conference},
isbn = {9780992862602},
issn = {22195491},
keywords = {Bayesian methods,Inverse methods,blind image deconvolution,compressive sensing,parameter estimation},
organization = {IEEE},
pages = {1--5},
title = {{Variational Bayesian compressive blind image deconvolution}},
year = {2013}
}
Downloads: 0
{"_id":"XefCW73JhqGaFgGaK","bibbaseid":"amizic-spinoulas-molina-katsaggelos-variationalbayesiancompressiveblindimagedeconvolution-2013","author_short":["Amizic, B.","Spinoulas, L.","Molina, R.","Katsaggelos, A. K."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","abstract":"We propose a novel variational Bayesian framework to perform simultaneous compressive sensing (CS) image reconstruction and blind deconvolution (BID) as well as estimate all modeling parameters. Furthermore, we show that the proposed framework generalizes the alternating direction method of multipliers which is often utilized to transform a constrained optimization problem into an unconstrained one through the use of the augmented Lagrangian. The proposed framework can be easily adapted to other signal processing applications or particular image and blur priors within the proposed context. In this work, as an example, we employ the following priors to illustrate the significance of the proposed approach: (1) a non-convex lp quasi-norm based prior for the image, (2) a simultaneous auto-regressive prior for the blur, and (3) an l1 norm based prior for the transformed coefficients. Experimental results using synthetic images demonstrate the advantages of the proposed algorithm over existing approaches. © 2013 EURASIP.","author":[{"propositions":[],"lastnames":["Amizic"],"firstnames":["Bruno"],"suffixes":[]},{"propositions":[],"lastnames":["Spinoulas"],"firstnames":["Leonidas"],"suffixes":[]},{"propositions":[],"lastnames":["Molina"],"firstnames":["Rafael"],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["Aggelos","K."],"suffixes":[]}],"booktitle":"European Signal Processing Conference","isbn":"9780992862602","issn":"22195491","keywords":"Bayesian methods,Inverse methods,blind image deconvolution,compressive sensing,parameter estimation","organization":"IEEE","pages":"1–5","title":"Variational Bayesian compressive blind image deconvolution","year":"2013","bibtex":"@inproceedings{amizic2013variational,\nabstract = {We propose a novel variational Bayesian framework to perform simultaneous compressive sensing (CS) image reconstruction and blind deconvolution (BID) as well as estimate all modeling parameters. Furthermore, we show that the proposed framework generalizes the alternating direction method of multipliers which is often utilized to transform a constrained optimization problem into an unconstrained one through the use of the augmented Lagrangian. The proposed framework can be easily adapted to other signal processing applications or particular image and blur priors within the proposed context. In this work, as an example, we employ the following priors to illustrate the significance of the proposed approach: (1) a non-convex lp quasi-norm based prior for the image, (2) a simultaneous auto-regressive prior for the blur, and (3) an l1 norm based prior for the transformed coefficients. Experimental results using synthetic images demonstrate the advantages of the proposed algorithm over existing approaches. {\\textcopyright} 2013 EURASIP.},\nauthor = {Amizic, Bruno and Spinoulas, Leonidas and Molina, Rafael and Katsaggelos, Aggelos K.},\nbooktitle = {European Signal Processing Conference},\nisbn = {9780992862602},\nissn = {22195491},\nkeywords = {Bayesian methods,Inverse methods,blind image deconvolution,compressive sensing,parameter estimation},\norganization = {IEEE},\npages = {1--5},\ntitle = {{Variational Bayesian compressive blind image deconvolution}},\nyear = {2013}\n}\n","author_short":["Amizic, B.","Spinoulas, L.","Molina, R.","Katsaggelos, A. K."],"key":"amizic2013variational","id":"amizic2013variational","bibbaseid":"amizic-spinoulas-molina-katsaggelos-variationalbayesiancompressiveblindimagedeconvolution-2013","role":"author","urls":{},"keyword":["Bayesian methods","Inverse methods","blind image deconvolution","compressive sensing","parameter estimation"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://sites.northwestern.edu/ivpl/files/2023/06/IVPL_Updated_publications-1.bib","dataSources":["KTWAakbPXLGfYseXn","ePKPjG8C6yvpk4mEK","D8k2SxfC5dKNRFgro","7Dwzbxq93HWrJEhT6","qhF8zxmGcJfvtdeAg","fvDEHD49E2ZRwE3fb","H7crv8NWhZup4d4by","DHqokWsryttGh7pJE","vRJd4wNg9HpoZSMHD","sYxQ6pxFgA59JRhxi","w2WahSbYrbcCKBDsC","XasdXLL99y5rygCmq","3gkSihZQRfAD2KBo3","t5XMbyZbtPBo4wBGS","bEpHM2CtrwW2qE8FP","teJzFLHexaz5AQW5z"],"keywords":["bayesian methods","inverse methods","blind image deconvolution","compressive sensing","parameter estimation"],"search_terms":["variational","bayesian","compressive","blind","image","deconvolution","amizic","spinoulas","molina","katsaggelos"],"title":"Variational Bayesian compressive blind image deconvolution","year":2013}