Please use this identifier to cite or link to this item: https://doi.org/10.1109/CVPR.2012.6247651
Title: Aligning images in the wild
Authors: Lin, W.-Y.
Liu, L.
Matsushita, Y.
Low, K.-L. 
Liu, S.
Issue Date: 2012
Source: Lin, W.-Y.,Liu, L.,Matsushita, Y.,Low, K.-L.,Liu, S. (2012). Aligning images in the wild. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition : 1-8. ScholarBank@NUS Repository. https://doi.org/10.1109/CVPR.2012.6247651
Abstract: Aligning image pairs with significant appearance change is a long standing computer vision challenge. Much of this problem stems from the local patch descriptors' instability to appearance variation. In this paper we suggest this instability is due less to descriptor corruption and more the difficulty in utilizing local information to canoni-cally define the orientation (scale and rotation) at which a patch's descriptor should be computed. We address this issue by jointly estimating correspondence and relative patch orientation, within a hierarchical algorithm that utilizes a smoothly varying parameterization of geometric transformations. By collectively estimating the correspondence and orientation of all the features, we can align and orient features that cannot be stably matched with only local information. At the price of smoothing over motion discontinuities (due to independent motion or parallax), this approach can align image pairs that display significant inter-image appearance variations. © 2012 IEEE.
Source Title: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
URI: http://scholarbank.nus.edu.sg/handle/10635/40004
ISBN: 9781467312264
ISSN: 10636919
DOI: 10.1109/CVPR.2012.6247651
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

19
checked on Dec 13, 2017

Page view(s)

55
checked on Dec 9, 2017

Google ScholarTM

Check

Altmetric


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