Multi-view-based siamese convolutional neural network for 3D object retrieval. (September 2019)

• Record Type: Journal Article
• Authors: Li, Haisheng; Zheng, Yanping; Cao, Jian; Cai, Qiang
• Is Part Of: Computers & electrical engineering. Volume 78(2019)
• Page Start: 11
• Page End: 21
• Publication Date: 2019-09
• Subjects: 3D object retrieval -- View-based -- Siamese network -- Convolutional neural network; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2019.06.022
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Representing three-dimensional (3D) objects by multiple views has become a common solution to the problem of 3D object retrieval. It has gained excellent achievements because of its remarkable adaptability and flexibility. In this paper, we develop a multi-view-based Siamese convolutional neural network for 3D object retrieval. It consists of two sub-networks which have the same architecture and also share the same set of weights. First, we generate a set of RGB images and binary images for each 3D object to capture local and global features. Second, the two sub-networks take corresponding images as input and avoid camera constraint by using average fusion layers. The final compact descriptors are learned by integrating features of sub-networks and then used for retrieval. Experimental results on two benchmarks, the PSB dataset and ETH dataset, testify that our proposed method receives superior retrieval performance compared to state-of-the-art methods.