DeepShape: Deep-Learned Shape Descriptor for 3D Shape Retrieval

Jin Xie, Guoxian Dai, Fan Zhu, Edward K. Wong, Yi Fang

Research output: Contribution to journalArticlepeer-review


Complex geometric variations of 3D models usually pose great challenges in 3D shape matching and retrieval. In this paper, we propose a novel 3D shape feature learning method to extract high-level shape features that are insensitive to geometric deformations of shapes. Our method uses a discriminative deep auto-encoder to learn deformation-invariant shape features. First, a multiscale shape distribution is computed and used as input to the auto-encoder. We then impose the Fisher discrimination criterion on the neurons in the hidden layer to develop a deep discriminative auto-encoder. Finally, the outputs from the hidden layers of the discriminative auto-encoders at different scales are concatenated to form the shape descriptor. The proposed method is evaluated on four benchmark datasets that contain 3D models with large geometric variations: McGill, SHREC'10 ShapeGoogle, SHREC'14 Human and SHREC'14 Large Scale Comprehensive Retrieval Track Benchmark datasets. Experimental results on the benchmark datasets demonstrate the effectiveness of the proposed method for 3D shape retrieval.

Original languageEnglish (US)
Article number7526450
Pages (from-to)1335-1345
Number of pages11
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number7
StatePublished - Jul 1 2017


  • 3D shape retrieval
  • Fisher discrimination criterion
  • auto-encoder
  • heat diffusion
  • heat kernel signature

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics


Dive into the research topics of 'DeepShape: Deep-Learned Shape Descriptor for 3D Shape Retrieval'. Together they form a unique fingerprint.

Cite this