Aligning images in the wild

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 difficul...

Full description

Saved in:
Bibliographic Details
Main Authors: LIN, Wen-yan, LIU, Linlin, MATSUSHITA, Yasuyuki, LOW, Kok-Lim, LIU, Siying
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2012
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/4807
https://ink.library.smu.edu.sg/context/sis_research/article/5810/viewcontent/10.1.1.227.4441.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-5810
record_format dspace
spelling sg-smu-ink.sis_research-58102020-01-16T10:04:17Z Aligning images in the wild LIN, Wen-yan LIU, Linlin MATSUSHITA, Yasuyuki LOW, Kok-Lim LIU, Siying 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 canonically 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. 2012-06-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/4807 info:doi/10.1109/CVPR.2012.6247651 https://ink.library.smu.edu.sg/context/sis_research/article/5810/viewcontent/10.1.1.227.4441.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Graphics and Human Computer Interfaces Programming Languages and Compilers
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Graphics and Human Computer Interfaces
Programming Languages and Compilers
spellingShingle Graphics and Human Computer Interfaces
Programming Languages and Compilers
LIN, Wen-yan
LIU, Linlin
MATSUSHITA, Yasuyuki
LOW, Kok-Lim
LIU, Siying
Aligning images in the wild
description 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 canonically 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.
format text
author LIN, Wen-yan
LIU, Linlin
MATSUSHITA, Yasuyuki
LOW, Kok-Lim
LIU, Siying
author_facet LIN, Wen-yan
LIU, Linlin
MATSUSHITA, Yasuyuki
LOW, Kok-Lim
LIU, Siying
author_sort LIN, Wen-yan
title Aligning images in the wild
title_short Aligning images in the wild
title_full Aligning images in the wild
title_fullStr Aligning images in the wild
title_full_unstemmed Aligning images in the wild
title_sort aligning images in the wild
publisher Institutional Knowledge at Singapore Management University
publishDate 2012
url https://ink.library.smu.edu.sg/sis_research/4807
https://ink.library.smu.edu.sg/context/sis_research/article/5810/viewcontent/10.1.1.227.4441.pdf
_version_ 1770575051889836032