Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICIP.2013.6738159
Title: Dense image correspondence under large appearance variations
Authors: Liu, L.
Low, K.-L. 
Lin, W.-Y.
Keywords: belief propagation
image matching
image motion analysis
image registration
SIFT Flow
Issue Date: 2013
Source: Liu, L.,Low, K.-L.,Lin, W.-Y. (2013). Dense image correspondence under large appearance variations. 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings : 770-774. ScholarBank@NUS Repository. https://doi.org/10.1109/ICIP.2013.6738159
Abstract: This paper addresses the difficult problem of finding dense correspondence across images with large appearance variations. Our method uses multiple feature samples at each pixel to deal with the appearance variations based on our observation that pre-defined single feature sample provides poor results in nearest neighbor matching. We apply the idea in a flow-based matching framework and utilize the best feature sample for each pixel to determine the flow field. We propose a novel energy function and use dual-layer loopy belief propagation to minimize it where the correspondence, the feature scale and rotation parameters are solved simultaneously. Our method is effective and produces generally better results. © 2013 IEEE.
Source Title: 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings
URI: http://scholarbank.nus.edu.sg/handle/10635/78087
ISBN: 9781479923410
DOI: 10.1109/ICIP.2013.6738159
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

3
checked on Feb 20, 2018

Page view(s)

42
checked on Feb 16, 2018

Google ScholarTM

Check

Altmetric


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