Non-rigid 3D Shape Retrieval via Sparse Representation

Wan, Lili; Li, Shuai; Miao, Zhenjiang J.; Cen, Yigang G.

Non-rigid 3D Shape Retrieval via Sparse Representation

Files

011-016.pdf (2.32 MB)

Date

2013

Authors

Wan, Lili
Li, Shuai
Miao, Zhenjiang J.
Cen, Yigang G.

Publisher

The Eurographics Association

Abstract

Shape descriptor design is an important but challenging problem for non-rigid 3D shape retrieval. Recently, bagof- words based methods are widely used to integrate a model's local shape descriptors into a global histogram. In this paper, we present a new method to pool the local shape descriptors into a global shape descriptor by means of sparse representation. Firstly, we employ heat kernel signature (HKS) to depict the multi-scale local shape. Then, for each model in the training dataset, we take the HKSs corresponding to its mesh vertices to serve as training signals, and thus an over-complete dictionary can be learned from them. Finally, the HKSs of each 3D model are sparsely coded based on the learned dictionary, and such sparse representations can be further integrated to form an object-level shape descriptor. Moreover, we conduct extensive experiments on the state-of-the-art benchmarks, wherein comprehensive evaluations state our method can achieve better performance than other bag-of-words based approaches.

        @inproceedings{10.2312:PE.PG.PG2013short.011-016
,
booktitle = {Pacific Graphics Short Papers
},
editor = {Bruno Levy and Xin Tong and KangKang Yin
},
title = {{Non-rigid 3D Shape Retrieval via Sparse Representation
}},
author = {Wan, Lili and 
Li, Shuai and 
Miao, Zhenjiang J. and 
Cen, Yigang G.
},
year = {2013
},
publisher = {The Eurographics Association
},
ISBN = {978-3-905674-50-7
},
DOI = {10.2312/PE.PG.PG2013short.011-016
}
}