Spectral Analysis Driven Sparse Matching of 3D Shapes

Darom, Tal; Keller, Yosi

Spectral Analysis Driven Sparse Matching of 3D Shapes

Files

059-062.pdf (575.97 KB)

Date

2012

Authors

Darom, Tal
Keller, Yosi

Publisher

The Eurographics Association

Abstract

In this work we present an approach for matching three-dimensional mesh objects related by isometric transfor- mations and scaling. We propose to utilize the Scale invariant Scale-DoG detector and Local Depth SIFT mesh descriptor, to derive a statistical voting-based scheme to robustly estimate the scale ratio between the registered meshes. This paves the way to formulating a novel non-rigid mesh registration scheme, by matching sets of sparse salient feature points using spectral graph matching. The resulting approach is shown to compare favorably with previous state-of-the-art approaches in registering meshes related by partial alignment, while being a few orders of magnitude faster.

        @inproceedings{:10.2312/3DOR/3DOR12/059-062
,
booktitle = {Eurographics Workshop on 3D Object Retrieval
},
editor = {M. Spagnuolo and M. Bronstein and A. Bronstein and A. Ferreira
},
title = {{Spectral Analysis Driven Sparse Matching of 3D Shapes
}},
author = {Darom, Tal and 
Keller, Yosi
},
year = {2012
},
publisher = {The Eurographics Association
},
ISSN = {1997-0463
},
ISBN = {978-3-905674-36-1
},
DOI = {/10.2312/3DOR/3DOR12/059-062
}
}