dc.contributor.author | Durand, Fredo | |
dc.contributor.author | Levin, Anat | |
dc.contributor.author | Weiss, Yair | |
dc.contributor.author | Freeman, William T. | |
dc.date.accessioned | 2010-11-04T18:11:54Z | |
dc.date.available | 2010-11-04T18:11:54Z | |
dc.date.issued | 2009-08 | |
dc.date.submitted | 2009-06 | |
dc.identifier.isbn | 978-1-4244-3992-8 | |
dc.identifier.ismn | 1063-6919 | |
dc.identifier.other | INSPEC Accession Number: 10836014 | |
dc.identifier.uri | http://hdl.handle.net/1721.1/59815 | |
dc.description.abstract | Blind deconvolution is the recovery of a sharp version of a blurred image when the blur kernel is unknown. Recent algorithms have afforded dramatic progress, yet many aspects of the problem remain challenging and hard to understand. The goal of this paper is to analyze and evaluate recent blind deconvolution algorithms both theoretically and experimentally. We explain the previously reported failure of the naive MAP approach by demonstrating that it mostly favors no-blur explanations. On the other hand we show that since the kernel size is often smaller than the image size a MAP estimation of the kernel alone can be well constrained and accurately recover the true blur. The plethora of recent deconvolution techniques makes an experimental evaluation on ground-truth data important. We have collected blur data with ground truth and compared recent algorithms under equal settings. Additionally, our data demonstrates that the shift-invariant blur assumption made by most algorithms is often violated. | en_US |
dc.description.sponsorship | Israeli Science Foundation | en_US |
dc.description.sponsorship | Royal Dutch/Shell Group | en_US |
dc.description.sponsorship | United States. National Geospatial-Intelligence Agency (NEGI-1582- 04-0004) | en_US |
dc.description.sponsorship | National Science Foundation (U.S.) (MURI Grant N00014-06-1-0734) | en_US |
dc.description.sponsorship | National Science Foundation (U.S.) (NSF CAREER award 0447561) | en_US |
dc.description.sponsorship | Microsoft Research New Faculty Fellowship | en_US |
dc.description.sponsorship | Alfred P. Sloan Foundation (Sloan Fellowship) | en_US |
dc.language.iso | en_US | |
dc.publisher | Institute of Electrical and Electronics Engineers | en_US |
dc.relation.isversionof | http://dx.doi.org/10.1109/CVPRW.2009.5206815 | en_US |
dc.rights | Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. | en_US |
dc.source | IEEE | en_US |
dc.title | Understanding and evaluating blind deconvolution algorithms | en_US |
dc.type | Article | en_US |
dc.identifier.citation | Levin, A. et al. “Understanding and evaluating blind deconvolution algorithms.” Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on. 2009. 1964-1971. ©2009 Institute of Electrical and Electronics Engineers. | en_US |
dc.contributor.department | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory | en_US |
dc.contributor.department | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science | en_US |
dc.contributor.approver | Durand, Fredo | |
dc.contributor.mitauthor | Durand, Fredo | |
dc.contributor.mitauthor | Levin, Anat | |
dc.contributor.mitauthor | Weiss, Yair | |
dc.contributor.mitauthor | Freeman, William T. | |
dc.relation.journal | IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009 | en_US |
dc.eprint.version | Final published version | en_US |
dc.type.uri | http://purl.org/eprint/type/JournalArticle | en_US |
eprint.status | http://purl.org/eprint/status/PeerReviewed | en_US |
dspace.orderedauthors | Levin, A.; Weiss, Y.; Durand, F.; Freeman, W.T. | en |
dc.identifier.orcid | https://orcid.org/0000-0001-9919-069X | |
dc.identifier.orcid | https://orcid.org/0000-0002-2231-7995 | |
mit.license | PUBLISHER_POLICY | en_US |
mit.metadata.status | Complete | |