Deepshape: Deep learned shape descriptor for 3D shape matching and retrieval

Jin Xie, Yi Fang, Fan Zhu, Edward Wong

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

Abstract

Complex geometric structural variations of 3D model usually pose great challenges in 3D shape matching and retrieval. In this paper, we propose a high-level shape feature learning scheme to extract features that are insensitive to deformations via a novel discriminative deep auto-encoder. First, a multiscale shape distribution is developed for use as input to the auto-encoder. Then, by imposing the Fisher discrimination criterion on the neurons in the hidden layer, we developed a novel discriminative deep auto-encoder for shape feature learning. Finally, the neurons in the hidden layers from multiple discriminative auto-encoders are concatenated to form a shape descriptor for 3D shape matching and retrieval. The proposed method is evaluated on the representative datasets that contain 3D models with large geometric variations, i.e., Mcgill and SHREC'10 ShapeGoogle datasets. Experimental results on the benchmark datasets demonstrate the effectiveness of the proposed method for 3D shape matching and retrieval.

Original languageEnglish (US)
Title of host publicationIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
PublisherIEEE Computer Society
Pages1275-1283
Number of pages9
Volume07-12-June-2015
ISBN (Print)9781467369640
DOIs
StatePublished - Oct 14 2015
EventIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 - Boston, United States
Duration: Jun 7 2015Jun 12 2015

Other

OtherIEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
CountryUnited States
CityBoston
Period6/7/156/12/15

Fingerprint

Neurons

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Xie, J., Fang, Y., Zhu, F., & Wong, E. (2015). Deepshape: Deep learned shape descriptor for 3D shape matching and retrieval. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015 (Vol. 07-12-June-2015, pp. 1275-1283). [7298732] IEEE Computer Society. https://doi.org/10.1109/CVPR.2015.7298732

Deepshape : Deep learned shape descriptor for 3D shape matching and retrieval. / Xie, Jin; Fang, Yi; Zhu, Fan; Wong, Edward.

IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. Vol. 07-12-June-2015 IEEE Computer Society, 2015. p. 1275-1283 7298732.

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

Xie, J, Fang, Y, Zhu, F & Wong, E 2015, Deepshape: Deep learned shape descriptor for 3D shape matching and retrieval. in IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. vol. 07-12-June-2015, 7298732, IEEE Computer Society, pp. 1275-1283, IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, United States, 6/7/15. https://doi.org/10.1109/CVPR.2015.7298732
Xie J, Fang Y, Zhu F, Wong E. Deepshape: Deep learned shape descriptor for 3D shape matching and retrieval. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. Vol. 07-12-June-2015. IEEE Computer Society. 2015. p. 1275-1283. 7298732 https://doi.org/10.1109/CVPR.2015.7298732
Xie, Jin ; Fang, Yi ; Zhu, Fan ; Wong, Edward. / Deepshape : Deep learned shape descriptor for 3D shape matching and retrieval. IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015. Vol. 07-12-June-2015 IEEE Computer Society, 2015. pp. 1275-1283
@inproceedings{0e66b16abee94cbf8e7668dff8f56335,
title = "Deepshape: Deep learned shape descriptor for 3D shape matching and retrieval",
abstract = "Complex geometric structural variations of 3D model usually pose great challenges in 3D shape matching and retrieval. In this paper, we propose a high-level shape feature learning scheme to extract features that are insensitive to deformations via a novel discriminative deep auto-encoder. First, a multiscale shape distribution is developed for use as input to the auto-encoder. Then, by imposing the Fisher discrimination criterion on the neurons in the hidden layer, we developed a novel discriminative deep auto-encoder for shape feature learning. Finally, the neurons in the hidden layers from multiple discriminative auto-encoders are concatenated to form a shape descriptor for 3D shape matching and retrieval. The proposed method is evaluated on the representative datasets that contain 3D models with large geometric variations, i.e., Mcgill and SHREC'10 ShapeGoogle datasets. Experimental results on the benchmark datasets demonstrate the effectiveness of the proposed method for 3D shape matching and retrieval.",
author = "Jin Xie and Yi Fang and Fan Zhu and Edward Wong",
year = "2015",
month = "10",
day = "14",
doi = "10.1109/CVPR.2015.7298732",
language = "English (US)",
isbn = "9781467369640",
volume = "07-12-June-2015",
pages = "1275--1283",
booktitle = "IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Deepshape

T2 - Deep learned shape descriptor for 3D shape matching and retrieval

AU - Xie, Jin

AU - Fang, Yi

AU - Zhu, Fan

AU - Wong, Edward

PY - 2015/10/14

Y1 - 2015/10/14

N2 - Complex geometric structural variations of 3D model usually pose great challenges in 3D shape matching and retrieval. In this paper, we propose a high-level shape feature learning scheme to extract features that are insensitive to deformations via a novel discriminative deep auto-encoder. First, a multiscale shape distribution is developed for use as input to the auto-encoder. Then, by imposing the Fisher discrimination criterion on the neurons in the hidden layer, we developed a novel discriminative deep auto-encoder for shape feature learning. Finally, the neurons in the hidden layers from multiple discriminative auto-encoders are concatenated to form a shape descriptor for 3D shape matching and retrieval. The proposed method is evaluated on the representative datasets that contain 3D models with large geometric variations, i.e., Mcgill and SHREC'10 ShapeGoogle datasets. Experimental results on the benchmark datasets demonstrate the effectiveness of the proposed method for 3D shape matching and retrieval.

AB - Complex geometric structural variations of 3D model usually pose great challenges in 3D shape matching and retrieval. In this paper, we propose a high-level shape feature learning scheme to extract features that are insensitive to deformations via a novel discriminative deep auto-encoder. First, a multiscale shape distribution is developed for use as input to the auto-encoder. Then, by imposing the Fisher discrimination criterion on the neurons in the hidden layer, we developed a novel discriminative deep auto-encoder for shape feature learning. Finally, the neurons in the hidden layers from multiple discriminative auto-encoders are concatenated to form a shape descriptor for 3D shape matching and retrieval. The proposed method is evaluated on the representative datasets that contain 3D models with large geometric variations, i.e., Mcgill and SHREC'10 ShapeGoogle datasets. Experimental results on the benchmark datasets demonstrate the effectiveness of the proposed method for 3D shape matching and retrieval.

UR - http://www.scopus.com/inward/record.url?scp=84959241349&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959241349&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2015.7298732

DO - 10.1109/CVPR.2015.7298732

M3 - Conference contribution

AN - SCOPUS:84959241349

SN - 9781467369640

VL - 07-12-June-2015

SP - 1275

EP - 1283

BT - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015

PB - IEEE Computer Society

ER -