Understanding and evaluating blind deconvolution algorithms
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 deco...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers
2010
|
| Online Access: | http://hdl.handle.net/1721.1/59815 https://orcid.org/0000-0001-9919-069X https://orcid.org/0000-0002-2231-7995 |
| _version_ | 1826210406872383488 |
|---|---|
| author | Durand, Fredo Levin, Anat Weiss, Yair Freeman, William T. |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Durand, Fredo Levin, Anat Weiss, Yair Freeman, William T. |
| author_sort | Durand, Fredo |
| collection | MIT |
| description | 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. |
| first_indexed | 2024-09-23T14:49:17Z |
| format | Article |
| id | mit-1721.1/59815 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T14:49:17Z |
| publishDate | 2010 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | mit-1721.1/598152022-09-29T10:46:28Z Understanding and evaluating blind deconvolution algorithms Durand, Fredo Levin, Anat Weiss, Yair Freeman, William T. Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Durand, Fredo Durand, Fredo Levin, Anat Weiss, Yair Freeman, William T. 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. Israeli Science Foundation Royal Dutch/Shell Group United States. National Geospatial-Intelligence Agency (NEGI-1582- 04-0004) National Science Foundation (U.S.) (MURI Grant N00014-06-1-0734) National Science Foundation (U.S.) (NSF CAREER award 0447561) Microsoft Research New Faculty Fellowship Alfred P. Sloan Foundation (Sloan Fellowship) 2010-11-04T18:11:54Z 2010-11-04T18:11:54Z 2009-08 2009-06 Article http://purl.org/eprint/type/JournalArticle 978-1-4244-3992-8 1063-6919 INSPEC Accession Number: 10836014 http://hdl.handle.net/1721.1/59815 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. https://orcid.org/0000-0001-9919-069X https://orcid.org/0000-0002-2231-7995 en_US http://dx.doi.org/10.1109/CVPRW.2009.5206815 IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009 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. application/pdf Institute of Electrical and Electronics Engineers IEEE |
| spellingShingle | Durand, Fredo Levin, Anat Weiss, Yair Freeman, William T. Understanding and evaluating blind deconvolution algorithms |
| title | Understanding and evaluating blind deconvolution algorithms |
| title_full | Understanding and evaluating blind deconvolution algorithms |
| title_fullStr | Understanding and evaluating blind deconvolution algorithms |
| title_full_unstemmed | Understanding and evaluating blind deconvolution algorithms |
| title_short | Understanding and evaluating blind deconvolution algorithms |
| title_sort | understanding and evaluating blind deconvolution algorithms |
| url | http://hdl.handle.net/1721.1/59815 https://orcid.org/0000-0001-9919-069X https://orcid.org/0000-0002-2231-7995 |
| work_keys_str_mv | AT durandfredo understandingandevaluatingblinddeconvolutionalgorithms AT levinanat understandingandevaluatingblinddeconvolutionalgorithms AT weissyair understandingandevaluatingblinddeconvolutionalgorithms AT freemanwilliamt understandingandevaluatingblinddeconvolutionalgorithms |