Dense image correspondence under large appearance variations

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 resul...

Full description

Saved in:
Bibliographic Details
Published in2013 IEEE International Conference on Image Processing pp. 770 - 774
Main Authors Linlin Liu, Kok-Lim Low, Wen-Yan Lin
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2013
Subjects
Belief propagation
Computational modeling
Computer vision
Conferences
Educational institutions
Image color analysis
Image matching
image motion analysis
image registration
SIFT Flow
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:1522-4880
2381-8549
DOI:10.1109/ICIP.2013.6738159