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

  • Xie J
  • Fang Y
  • Zhu F
 et al. 
  • 146

    Readers

    Mendeley users who have this article in their library.
  • 47

    Citations

    Citations of this article.

Abstract

Complex geometric structural variations of 3D model usually pose great challenges in 3D shape matching and re- trieval. 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 con- catenated to form a shape descriptor for 3D shape matching and retrieval. The proposed method is evaluated on the rep- resentative datasets that contain 3D models with large geo- metric 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

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document

Authors

  • Jin Xie

  • Yi Fang

  • Fan Zhu

  • Edward Wong

Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free