A Unified Spectral Embedding for Shape Correspondence

Zizhao Wu, Ruyang Shou, Xinguo Liu

2013

Abstract

Spectral embedding, as one of shape representative techniques, takes hold of many researchers’ attention in field of shape correspondence. One of the biggest challenges of spectral correspondence method is that embeddings of different shapes need to be aligned in the embedding space in order to eliminate sign flip and ordering ambiguity of their eigenfunctions, before seeking for correspondence. In this paper, we introduce a spectral correspondence method by embedding shapes in a unified space simultaneously. In the unified embedding space, the sample points of the same shape with small intrinsic distances, and from different shapes with high similarity, are close to each other. Our unified embedding can be used for correspondence directly, without need of alignment. Furthermore, the unified embedding captures both the spatial arrangement and the feature similarity. Shape correspondence is achieved with such embedding by minimizing an objective function. Results show the efficiency of our method.

Paper Citation

in Harvard Style

Wu Z., Shou R. and Liu X. (2013). A Unified Spectral Embedding for Shape Correspondence . In Proceedings of the International Conference on Computer Graphics Theory and Applications and International Conference on Information Visualization Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2013) ISBN 978-989-8565-46-4, pages 94-99. DOI: 10.5220/0004278700940099

in Bibtex Style

@conference{grapp13,
author={Zizhao Wu and Ruyang Shou and Xinguo Liu},
title={A Unified Spectral Embedding for Shape Correspondence},
booktitle={Proceedings of the International Conference on Computer Graphics Theory and Applications and International Conference on Information Visualization Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2013)},
year={2013},
pages={94-99},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004278700940099},
isbn={978-989-8565-46-4},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Graphics Theory and Applications and International Conference on Information Visualization Theory and Applications - Volume 1: GRAPP, (VISIGRAPP 2013)
TI - A Unified Spectral Embedding for Shape Correspondence
SN - 978-989-8565-46-4
AU - Wu Z.
AU - Shou R.
AU - Liu X.
PY - 2013
SP - 94
EP - 99
DO - 10.5220/0004278700940099