Please use this identifier to cite or link to this item: https://doi.org/10.1109/CVPR.2010.5539941
DC FieldValue
dc.titleRobust flash deblurring
dc.contributor.authorZhuo, S.
dc.contributor.authorGuo, D.
dc.contributor.authorSim, T.
dc.date.accessioned2013-07-04T07:54:24Z
dc.date.available2013-07-04T07:54:24Z
dc.date.issued2010
dc.identifier.citationZhuo, S., Guo, D., Sim, T. (2010). Robust flash deblurring. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition : 2440-2447. ScholarBank@NUS Repository. https://doi.org/10.1109/CVPR.2010.5539941
dc.identifier.isbn9781424469840
dc.identifier.issn10636919
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/39999
dc.description.abstractMotion blur due to camera shake is an annoying yet common problem in low-light photography. In this paper, we propose a novel method to recover a sharp image from a pair of motion blurred and flash images, consecutively captured using a hand-held camera. We first introduce a robust flash gradient constraint by exploiting the correlation between a sharp image and its corresponding flash image. Then we formulate our flash deblurring as solving a maximum-a-posteriori problem under the flash gradient constraint. We solve the problem by performing kernel estimation and non-blind deconvolution iteratively, leading to an accurate blur kernel and a reconstructed image with fine image details. Experiments on both synthetic and real images show the superiority of our method compared with existing methods. ©2010 IEEE.
dc.description.urihttp://libproxy1.nus.edu.sg/login?url=http://dx.doi.org/10.1109/CVPR.2010.5539941
dc.sourceScopus
dc.typeConference Paper
dc.contributor.departmentCOMPUTER SCIENCE
dc.description.doi10.1109/CVPR.2010.5539941
dc.description.sourcetitleProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
dc.description.page2440-2447
dc.description.codenPIVRE
dc.identifier.isiut000287417502063
Appears in Collections:Staff Publications

Show simple item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

63
checked on Sep 15, 2020

WEB OF SCIENCETM
Citations

44
checked on Sep 15, 2020

Page view(s)

82
checked on Sep 15, 2020

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.