Skip to main content

Research Repository

Advanced Search

Web3D learning framework for 3D shape retrieval based on hybrid convolutional neural networks

Zhou, Wen; Jia, Jinyuan; Huang, Chengxi; Cheng, Yongqing

Authors

Wen Zhou

Jinyuan Jia

Chengxi Huang

Yongqing Cheng



Abstract

With the rapid development of Web3D technologies, sketch-based model retrieval has become an increasingly important challenge, while the application of Virtual Reality and 3D technologies has made shape retrieval of furniture over a web browser feasible. In this paper, we propose a learning framework for shape retrieval based on two Siamese VGG-16 Convolutional Neural Networks (CNNs), and a CNN-based hybrid learning algorithm to select the best view for a shape. In this algorithm, the AlexNet and VGG-16 CNN architectures are used to perform classification tasks and to extract features, respectively. In addition, a feature fusion method is used to measure the similarity relation of the output features from the two Siamese networks. The proposed framework can provide new alternatives for furniture retrieval in the Web3D environment. The primary innovation is in the employment of deep learning methods to solve the challenge of obtaining the best view of 3D furniture, and to address cross-domain feature learning problems. We conduct an experiment to verify the feasibility of the framework and the results show our approach to be superior in comparison to many mainstream state-of-the-art approaches.

Citation

Zhou, W., Jia, J., Huang, C., & Cheng, Y. (2020). Web3D learning framework for 3D shape retrieval based on hybrid convolutional neural networks. Tsinghua Science and Technology, 25(1), 93-102. https://doi.org/10.26599/TST.2018.9010113

Journal Article Type Article
Acceptance Date Jul 20, 2018
Online Publication Date Jul 22, 2019
Publication Date 2020-02
Deposit Date Aug 9, 2019
Publicly Available Date Mar 29, 2024
Journal Tsinghua Science and Technology
Print ISSN 1007-0214
Publisher Institute of Electrical and Electronics Engineers
Peer Reviewed Peer Reviewed
Volume 25
Issue 1
Pages 93-102
DOI https://doi.org/10.26599/TST.2018.9010113
Keywords Multidisciplinary
Public URL https://hull-repository.worktribe.com/output/2332873
Publisher URL https://ieeexplore.ieee.org/document/8768209

Files





You might also like



Downloadable Citations