Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

12-2013

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.

Keywords

belief propagation, image matching, image motion analysis, image registration, SIFT Flow

Discipline

Graphics and Human Computer Interfaces | Software Engineering

Research Areas

Data Science and Engineering

Publication

Proceedings of the 20th IEEE International Conference on Image Processing, ICIP 2013, Melbourne, Australia, September 15-18

First Page

770

Last Page

774

ISBN

9781479923410

Identifier

10.1109/ICIP.2013.6738159

City or Country

Melbourne, Australia

Additional URL

https://doi.org/10.1109/ICIP.2013.6738159

Download

Share

COinS