Abstract
Shape representation for 3D models is an impor- tant topic in computer vision, multimedia analysis and com- puter graphics. Recent multi-view based methods demonstrate promising performance for 3D shape recognition and retrieval. However, most multi-view based methods ignore the correlations of multiple views or suffer from high computional cost. In this paper, we propose a novel multi-view based network architecture for 3D shape recognition and retrieval. Our network combines Convolutional Neural Networks (CNN) with Long Short Term Memory (LSTM) to exploit the correlative information from multiple views. Well-pretrained CNNs with residual connections are first used to extract low-level feature of each view image rendered from a 3D shape. Then, LSTM and a sequence voting layer are employed to aggregate these features into a shape descriptor. Highway network and a three-step training strategy are also adopted to boost the optimization of the deep network. Experimental results on two public datasets demonstrate that the proposed method achieves promising performance for 3D shape recognition and the state-of-the-art performance for 3D shape retrieval.
Funding Information
  • National Natural Science Foundation of China (61602499, 61471371, 61401474)
  • Hunan Provincial Natural Science Foundation (2016JJ3025)
  • National Postdoctoral Program for Innovative Talents (BX201600172)
  • China Postdoctoral Science Foundation
  • Fundamental Research Funds for the Central Universities

This publication has 36 references indexed in Scilit: