Learned binary spectral shape descriptor for 3D shape correspondence

Jin Xie, Meng Wang, Yi Fang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Dense 3D shape correspondence is an important problem in computer vision and computer graphics. Recently, the local shape descriptor based 3D shape correspondence approaches have been widely studied, where the local shape descriptor is a real-valued vector to characterize the geometrical structure of the shape. Different from these realvalued local shape descriptors, in this paper, we propose to learn a novel binary spectral shape descriptor with the deep neural network for 3D shape correspondence. The binary spectral shape descriptor can require less storage space and enable fast matching. First, based on the eigenvectors of the Laplace-Beltrami operator, we construct a neural network to form a nonlinear spectral representation to characterize the shape. Then, for the defined positive and negative points on the shapes, we train the constructed neural network by minimizing the errors between the outputs and their corresponding binary descriptors, minimizing the variations of the outputs of the positive points and maximizing the variations of the outputs of the negative points, simultaneously. Finally, we binarize the output of the neural network to form the binary spectral shape descriptor for shape correspondence. The proposed binary spectral shape descriptor is evaluated on the SCAPE and TOSCA 3D shape datasets for shape correspondence. The experimental results demonstrate the effectiveness of the proposed binary shape descriptor for the shape correspondence task.

Original languageEnglish (US)
Title of host publication2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
PublisherIEEE Computer Society
Pages3309-3317
Number of pages9
Volume2016-January
ISBN (Electronic)9781467388511
StatePublished - Jan 1 2016
Event2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 - Las Vegas, United States
Duration: Jun 26 2016Jul 1 2016

Other

Other2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
CountryUnited States
CityLas Vegas
Period6/26/167/1/16

Fingerprint

Neural networks
Computer graphics
Eigenvalues and eigenfunctions
Computer vision
Deep neural networks

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Xie, J., Wang, M., & Fang, Y. (2016). Learned binary spectral shape descriptor for 3D shape correspondence. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 (Vol. 2016-January, pp. 3309-3317). IEEE Computer Society.

Learned binary spectral shape descriptor for 3D shape correspondence. / Xie, Jin; Wang, Meng; Fang, Yi.

2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. Vol. 2016-January IEEE Computer Society, 2016. p. 3309-3317.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Xie, J, Wang, M & Fang, Y 2016, Learned binary spectral shape descriptor for 3D shape correspondence. in 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. vol. 2016-January, IEEE Computer Society, pp. 3309-3317, 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, United States, 6/26/16.
Xie J, Wang M, Fang Y. Learned binary spectral shape descriptor for 3D shape correspondence. In 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. Vol. 2016-January. IEEE Computer Society. 2016. p. 3309-3317
Xie, Jin ; Wang, Meng ; Fang, Yi. / Learned binary spectral shape descriptor for 3D shape correspondence. 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. Vol. 2016-January IEEE Computer Society, 2016. pp. 3309-3317
@inproceedings{7a1ccda792694582b2bec6e77918b7cc,
title = "Learned binary spectral shape descriptor for 3D shape correspondence",
abstract = "Dense 3D shape correspondence is an important problem in computer vision and computer graphics. Recently, the local shape descriptor based 3D shape correspondence approaches have been widely studied, where the local shape descriptor is a real-valued vector to characterize the geometrical structure of the shape. Different from these realvalued local shape descriptors, in this paper, we propose to learn a novel binary spectral shape descriptor with the deep neural network for 3D shape correspondence. The binary spectral shape descriptor can require less storage space and enable fast matching. First, based on the eigenvectors of the Laplace-Beltrami operator, we construct a neural network to form a nonlinear spectral representation to characterize the shape. Then, for the defined positive and negative points on the shapes, we train the constructed neural network by minimizing the errors between the outputs and their corresponding binary descriptors, minimizing the variations of the outputs of the positive points and maximizing the variations of the outputs of the negative points, simultaneously. Finally, we binarize the output of the neural network to form the binary spectral shape descriptor for shape correspondence. The proposed binary spectral shape descriptor is evaluated on the SCAPE and TOSCA 3D shape datasets for shape correspondence. The experimental results demonstrate the effectiveness of the proposed binary shape descriptor for the shape correspondence task.",
author = "Jin Xie and Meng Wang and Yi Fang",
year = "2016",
month = "1",
day = "1",
language = "English (US)",
volume = "2016-January",
pages = "3309--3317",
booktitle = "2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Learned binary spectral shape descriptor for 3D shape correspondence

AU - Xie, Jin

AU - Wang, Meng

AU - Fang, Yi

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Dense 3D shape correspondence is an important problem in computer vision and computer graphics. Recently, the local shape descriptor based 3D shape correspondence approaches have been widely studied, where the local shape descriptor is a real-valued vector to characterize the geometrical structure of the shape. Different from these realvalued local shape descriptors, in this paper, we propose to learn a novel binary spectral shape descriptor with the deep neural network for 3D shape correspondence. The binary spectral shape descriptor can require less storage space and enable fast matching. First, based on the eigenvectors of the Laplace-Beltrami operator, we construct a neural network to form a nonlinear spectral representation to characterize the shape. Then, for the defined positive and negative points on the shapes, we train the constructed neural network by minimizing the errors between the outputs and their corresponding binary descriptors, minimizing the variations of the outputs of the positive points and maximizing the variations of the outputs of the negative points, simultaneously. Finally, we binarize the output of the neural network to form the binary spectral shape descriptor for shape correspondence. The proposed binary spectral shape descriptor is evaluated on the SCAPE and TOSCA 3D shape datasets for shape correspondence. The experimental results demonstrate the effectiveness of the proposed binary shape descriptor for the shape correspondence task.

AB - Dense 3D shape correspondence is an important problem in computer vision and computer graphics. Recently, the local shape descriptor based 3D shape correspondence approaches have been widely studied, where the local shape descriptor is a real-valued vector to characterize the geometrical structure of the shape. Different from these realvalued local shape descriptors, in this paper, we propose to learn a novel binary spectral shape descriptor with the deep neural network for 3D shape correspondence. The binary spectral shape descriptor can require less storage space and enable fast matching. First, based on the eigenvectors of the Laplace-Beltrami operator, we construct a neural network to form a nonlinear spectral representation to characterize the shape. Then, for the defined positive and negative points on the shapes, we train the constructed neural network by minimizing the errors between the outputs and their corresponding binary descriptors, minimizing the variations of the outputs of the positive points and maximizing the variations of the outputs of the negative points, simultaneously. Finally, we binarize the output of the neural network to form the binary spectral shape descriptor for shape correspondence. The proposed binary spectral shape descriptor is evaluated on the SCAPE and TOSCA 3D shape datasets for shape correspondence. The experimental results demonstrate the effectiveness of the proposed binary shape descriptor for the shape correspondence task.

UR - http://www.scopus.com/inward/record.url?scp=84986317497&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986317497&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2016-January

SP - 3309

EP - 3317

BT - 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016

PB - IEEE Computer Society

ER -