File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Seeing through the blur

TitleSeeing through the blur
Authors
Mobahi, HosseinZitnick, C. LawrenceMa, Yi
Issue Date2012
Citation
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2012, p. 1736-1743 How to Cite?
DOI: http://dx.doi.org/10.1109/CVPR.2012.6247869
AbstractThis paper addresses the problem of image alignment using direct intensity-based methods for affine and homography transformations. Direct methods often employ scale-space smoothing (Gaussian blur) of the images to avoid local minima. Although, it is known that the isotropic blur used is not optimal for some motion models, the correct blur kernels have not been rigorously derived for motion models beyond translations. In this work, we derive blur kernels that result from smoothing the alignment objective function for some common motion models such as affine and homography. We show the derived kernels remove poor local minima and reach lower energy solutions in practice. © 2012 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/326906
ISSN
1063-6919
2023 SCImago Journal Rankings: 10.331

 

DC FieldValueLanguage
dc.contributor.authorMobahi, Hossein-
dc.contributor.authorZitnick, C. Lawrence-
dc.contributor.authorMa, Yi-
dc.date.accessioned2023-03-31T05:27:24Z-
dc.date.available2023-03-31T05:27:24Z-
dc.date.issued2012-
dc.identifier.citationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2012, p. 1736-1743-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10722/326906-
dc.description.abstractThis paper addresses the problem of image alignment using direct intensity-based methods for affine and homography transformations. Direct methods often employ scale-space smoothing (Gaussian blur) of the images to avoid local minima. Although, it is known that the isotropic blur used is not optimal for some motion models, the correct blur kernels have not been rigorously derived for motion models beyond translations. In this work, we derive blur kernels that result from smoothing the alignment objective function for some common motion models such as affine and homography. We show the derived kernels remove poor local minima and reach lower energy solutions in practice. © 2012 IEEE.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition-
dc.titleSeeing through the blur-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/CVPR.2012.6247869-
dc.identifier.scopuseid_2-s2.0-84866685271-
dc.identifier.spage1736-
dc.identifier.epage1743-

Export via OAI-PMH Interface in XML Formats

OR

Export to Other Non-XML Formats