Multiscale Features for Approximate Alignment of Point-based Surfaces

Li, Xinju; Guskov, Igor

Multiscale Features for Approximate Alignment of Point-based Surfaces

Files

217-226.pdf (13.23 MB)

Date

2005

Authors

Li, Xinju
Guskov, Igor

Publisher

The Eurographics Association

Abstract

We introduce a novel method for approximate alignment of point-based surfaces. Our approach is based on detecting a set of salient feature points using a scale-space representation. For each feature point we compute a signature vector that is approximately invariant under rigid transformations. We use the extracted signed feature set in order to obtain approximate alignment of two surfaces. We apply our method for the automatic alignment of multiple scans using both scan-to-scan and scan-to-model matching capabilities.

        @inproceedings{:10.2312/SGP/SGP05/217-226
,
booktitle = {Eurographics Symposium on Geometry Processing 2005
},
editor = {Mathieu Desbrun and Helmut Pottmann
},
title = {{Multiscale Features for Approximate Alignment of Point-based Surfaces
}},
author = {Li, Xinju and 
Guskov, Igor
},
year = {2005
},
publisher = {The Eurographics Association
},
ISSN = {1727-8384
},
ISBN = {3-905673-24-X
},
DOI = {/10.2312/SGP/SGP05/217-226
}
}