P000024
Unsupervised 3D shape segmentation and co-segmentation via deep learning
*Zhenyu Shu (School of Information Science and Engineering, Ningbo Institute of Technology, Zhejiang University)
Chengwu Qi (College of Electronic and Information Engineering, Taiyuan University of Science and Technology)
Ligang Liu (Graphics & Geometric Computing Laboratory, School of Mathematical Sciences, University of Science and Technology of China)
Shiqing Xin (School of Information Science and Engineering, Ningbo University)
Chao Hu (School of Information Science and Engineering, Ningbo Institute of Technology, Zhejiang University)
Li Wang (School of Information Science and Engineering, Ningbo Institute of Technology, Zhejiang University)
In this paper, we propose a novel unsupervised algorithm for automatically segmenting a 3D shape or co-segmenting a set of 3D shapes of the same family by using deep learning. Firstly, our approach decomposes each 3D shape into primitive patches to generate an over-segmentation. Secondly, high-level features are learned from the low-level ones for each patch by using the deep learning technique in an unsupervised way. Finally, the segmentation and co-segmentation results for each 3D shape are obtained by clustering the patches in the high-level feature space. The experimental results on Princeton segmentation benchmark and COSEG dataset demonstrate the superior performance of the proposed method in comparison to the state-of-the-art methods.