Rolling Shutter Motion Deblurring

Handle URI:
http://hdl.handle.net/10754/556518
Title:
Rolling Shutter Motion Deblurring
Authors:
Su, Shuochen; Heidrich, Wolfgang ( 0000-0002-4227-8508 )
Abstract:
Although motion blur and rolling shutter deformations are closely coupled artifacts in images taken with CMOS image sensors, the two phenomena have so far mostly been treated separately, with deblurring algorithms being unable to handle rolling shutter wobble, and rolling shutter algorithms being incapable of dealing with motion blur. We propose an approach that delivers sharp and undis torted output given a single rolling shutter motion blurred image. The key to achieving this is a global modeling of the camera motion trajectory, which enables each scanline of the image to be deblurred with the corresponding motion segment. We show the results of the proposed framework through experiments on synthetic and real data.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Publisher:
IEEE
Journal:
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
Conference/Event name:
Computer Vision and Pattern Recognition (CVPR),2015
Issue Date:
7-Jun-2015
Type:
Conference Paper
Additional Links:
http://www.cv-foundation.org/openaccess/content_cvpr_2015/app/1B_046.pdf
Appears in Collections:
Conference Papers; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorSu, Shuochenen
dc.contributor.authorHeidrich, Wolfgangen
dc.date.accessioned2015-06-07T22:00:53Zen
dc.date.available2015-06-07T22:00:53Zen
dc.date.issued2015-06-07en
dc.identifier.urihttp://hdl.handle.net/10754/556518en
dc.description.abstractAlthough motion blur and rolling shutter deformations are closely coupled artifacts in images taken with CMOS image sensors, the two phenomena have so far mostly been treated separately, with deblurring algorithms being unable to handle rolling shutter wobble, and rolling shutter algorithms being incapable of dealing with motion blur. We propose an approach that delivers sharp and undis torted output given a single rolling shutter motion blurred image. The key to achieving this is a global modeling of the camera motion trajectory, which enables each scanline of the image to be deblurred with the corresponding motion segment. We show the results of the proposed framework through experiments on synthetic and real data.en
dc.publisherIEEEen
dc.relation.urlhttp://www.cv-foundation.org/openaccess/content_cvpr_2015/app/1B_046.pdfen
dc.rightsThis CVPR 2015 paper is the Open Access version, provided by the Computer Vision Foundation. The authoritative version of this paper is available in IEEE Xplore.en
dc.titleRolling Shutter Motion Deblurringen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalProceedings of the IEEE Conference on Computer Vision and Pattern Recognitionen
dc.conference.date07 Jun - 12 Jun 2015en
dc.conference.nameComputer Vision and Pattern Recognition (CVPR),2015en
dc.conference.locationBoston, Massachusettsen
dc.eprint.versionPublisher's Version/PDFen
dc.contributor.institutionUniversity of British Columbiaen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.