File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/CVPR.2012.6247869
- Scopus: eid_2-s2.0-84866685271
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Seeing through the blur
Title | Seeing through the blur |
---|---|
Authors | |
Issue Date | 2012 |
Citation | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2012, p. 1736-1743 How to Cite? |
Abstract | This 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 Identifier | http://hdl.handle.net/10722/326906 |
ISSN | 2023 SCImago Journal Rankings: 10.331 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Mobahi, Hossein | - |
dc.contributor.author | Zitnick, C. Lawrence | - |
dc.contributor.author | Ma, Yi | - |
dc.date.accessioned | 2023-03-31T05:27:24Z | - |
dc.date.available | 2023-03-31T05:27:24Z | - |
dc.date.issued | 2012 | - |
dc.identifier.citation | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2012, p. 1736-1743 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/10722/326906 | - |
dc.description.abstract | This 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.language | eng | - |
dc.relation.ispartof | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | - |
dc.title | Seeing through the blur | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/CVPR.2012.6247869 | - |
dc.identifier.scopus | eid_2-s2.0-84866685271 | - |
dc.identifier.spage | 1736 | - |
dc.identifier.epage | 1743 | - |