Fast and robust multiframe super resolution. Farsiu, S., Robinson, M., Elad, M., & Milanfar, P. IEEE Transactions on Image Processing, 13(10):1327–1344, October, 2004. Conference Name: IEEE Transactions on Image Processingdoi abstract bibtex Super-resolution reconstruction produces one or a set of high-resolution images from a set of low-resolution images. In the last two decades, a variety of super-resolution methods have been proposed. These methods are usually very sensitive to their assumed model of data and noise, which limits their utility. This paper reviews some of these methods and addresses their shortcomings. We propose an alternate approach using L/sub 1/ norm minimization and robust regularization based on a bilateral prior to deal with different data and noise models. This computationally inexpensive method is robust to errors in motion and blur estimation and results in images with sharp edges. Simulation results confirm the effectiveness of our method and demonstrate its superiority to other super-resolution methods.
@article{farsiu_fast_2004,
title = {Fast and robust multiframe super resolution},
volume = {13},
issn = {1941-0042},
doi = {10.1109/TIP.2004.834669},
abstract = {Super-resolution reconstruction produces one or a set of high-resolution images from a set of low-resolution images. In the last two decades, a variety of super-resolution methods have been proposed. These methods are usually very sensitive to their assumed model of data and noise, which limits their utility. This paper reviews some of these methods and addresses their shortcomings. We propose an alternate approach using L/sub 1/ norm minimization and robust regularization based on a bilateral prior to deal with different data and noise models. This computationally inexpensive method is robust to errors in motion and blur estimation and results in images with sharp edges. Simulation results confirm the effectiveness of our method and demonstrate its superiority to other super-resolution methods.},
language = {en},
number = {10},
journal = {IEEE Transactions on Image Processing},
author = {Farsiu, S. and Robinson, M.D. and Elad, M. and Milanfar, P.},
month = oct,
year = {2004},
note = {Conference Name: IEEE Transactions on Image Processing},
keywords = {\#Analysis, \#Representation{\textgreater}SR, /unread, Cameras, Computational modeling, Frequency domain analysis, Image reconstruction, Image resolution, Layout, Lenses, Motion estimation, Noise robustness, Spatial resolution},
pages = {1327--1344},
}
Downloads: 0
{"_id":"uN256acS8LTzKToi5","bibbaseid":"farsiu-robinson-elad-milanfar-fastandrobustmultiframesuperresolution-2004","downloads":0,"creationDate":"2018-01-22T16:01:06.993Z","title":"Fast and robust multiframe super resolution","author_short":["Farsiu, S.","Robinson, M.","Elad, M.","Milanfar, P."],"year":2004,"bibtype":"article","biburl":"https://bibbase.org/zotero/zzhenry2012","bibdata":{"bibtype":"article","type":"article","title":"Fast and robust multiframe super resolution","volume":"13","issn":"1941-0042","doi":"10.1109/TIP.2004.834669","abstract":"Super-resolution reconstruction produces one or a set of high-resolution images from a set of low-resolution images. In the last two decades, a variety of super-resolution methods have been proposed. These methods are usually very sensitive to their assumed model of data and noise, which limits their utility. This paper reviews some of these methods and addresses their shortcomings. We propose an alternate approach using L/sub 1/ norm minimization and robust regularization based on a bilateral prior to deal with different data and noise models. This computationally inexpensive method is robust to errors in motion and blur estimation and results in images with sharp edges. Simulation results confirm the effectiveness of our method and demonstrate its superiority to other super-resolution methods.","language":"en","number":"10","journal":"IEEE Transactions on Image Processing","author":[{"propositions":[],"lastnames":["Farsiu"],"firstnames":["S."],"suffixes":[]},{"propositions":[],"lastnames":["Robinson"],"firstnames":["M.D."],"suffixes":[]},{"propositions":[],"lastnames":["Elad"],"firstnames":["M."],"suffixes":[]},{"propositions":[],"lastnames":["Milanfar"],"firstnames":["P."],"suffixes":[]}],"month":"October","year":"2004","note":"Conference Name: IEEE Transactions on Image Processing","keywords":"#Analysis, #Representation\\textgreaterSR, /unread, Cameras, Computational modeling, Frequency domain analysis, Image reconstruction, Image resolution, Layout, Lenses, Motion estimation, Noise robustness, Spatial resolution","pages":"1327–1344","bibtex":"@article{farsiu_fast_2004,\n\ttitle = {Fast and robust multiframe super resolution},\n\tvolume = {13},\n\tissn = {1941-0042},\n\tdoi = {10.1109/TIP.2004.834669},\n\tabstract = {Super-resolution reconstruction produces one or a set of high-resolution images from a set of low-resolution images. In the last two decades, a variety of super-resolution methods have been proposed. These methods are usually very sensitive to their assumed model of data and noise, which limits their utility. This paper reviews some of these methods and addresses their shortcomings. We propose an alternate approach using L/sub 1/ norm minimization and robust regularization based on a bilateral prior to deal with different data and noise models. This computationally inexpensive method is robust to errors in motion and blur estimation and results in images with sharp edges. Simulation results confirm the effectiveness of our method and demonstrate its superiority to other super-resolution methods.},\n\tlanguage = {en},\n\tnumber = {10},\n\tjournal = {IEEE Transactions on Image Processing},\n\tauthor = {Farsiu, S. and Robinson, M.D. and Elad, M. and Milanfar, P.},\n\tmonth = oct,\n\tyear = {2004},\n\tnote = {Conference Name: IEEE Transactions on Image Processing},\n\tkeywords = {\\#Analysis, \\#Representation{\\textgreater}SR, /unread, Cameras, Computational modeling, Frequency domain analysis, Image reconstruction, Image resolution, Layout, Lenses, Motion estimation, Noise robustness, Spatial resolution},\n\tpages = {1327--1344},\n}\n\n\n\n","author_short":["Farsiu, S.","Robinson, M.","Elad, M.","Milanfar, P."],"key":"farsiu_fast_2004","id":"farsiu_fast_2004","bibbaseid":"farsiu-robinson-elad-milanfar-fastandrobustmultiframesuperresolution-2004","role":"author","urls":{},"keyword":["#Analysis","#Representation\\textgreaterSR","/unread","Cameras","Computational modeling","Frequency domain analysis","Image reconstruction","Image resolution","Layout","Lenses","Motion estimation","Noise robustness","Spatial resolution"],"metadata":{"authorlinks":{}},"downloads":0,"html":""},"search_terms":["fast","robust","multiframe","super","resolution","farsiu","robinson","elad","milanfar"],"keywords":["#analysis","#representation\\textgreatersr","/unread","cameras","computational modeling","frequency domain analysis","image reconstruction","image resolution","layout","lenses","motion estimation","noise robustness","spatial resolution"],"authorIDs":[],"dataSources":["9cexBw6hrwgyZphZZ","nZHrFJKyxKKDaWYM8"]}