Next Article in Journal
Motion Planning for Vibration Reduction of a Railway Bridge Maintenance Robot with a Redundant Manipulator
Next Article in Special Issue
Real-Time Application of Computer Graphics Improvement Techniques Using Hyperspectral Textures in a Virtual Reality System
Previous Article in Journal
Power Conversion System Operation Algorithm for Efficient Energy Management of Microgrids
Article

FaceVAE: Generation of a 3D Geometric Object Using Variational Autoencoders

by 1,2 and 2,*
1
Korea Virtual Reality Inc., Seoul 05719, Korea
2
Department of Computer Science and Engineering, Korea University, Seoul 02841, Korea
*
Author to whom correspondence should be addressed.
Academic Editors: Hai Huang and Ye Duan
Electronics 2021, 10(22), 2792; https://doi.org/10.3390/electronics10222792
Received: 29 September 2021 / Revised: 4 November 2021 / Accepted: 11 November 2021 / Published: 14 November 2021
(This article belongs to the Special Issue New Advances in Visual Computing and Virtual Reality)
Deep learning for 3D data has become a popular research theme in many fields. However, most of the research on 3D data is based on voxels, 2D images, and point clouds. At actual industrial sites, face-based geometry data are being used, but their direct application to industrial sites remains limited due to a lack of existing research. In this study, to overcome these limitations, we present a face-based variational autoencoder (FVAE) model that generates 3D geometry data using a variational autoencoder (VAE) model directly from face-based geometric data. Our model improves the existing node and edge-based adjacency matrix and optimizes it for geometric learning by using a face- and edge-based adjacency matrix according to the 3D geometry structure. In the experiment, we achieved the result of generating adjacency matrix information with 72% precision and 69% recall through end-to-end learning of Face-Based 3D Geometry. In addition, we presented various structurization methods for 3D unstructured geometry and compared their performance, and proved the method to effectively perform reconstruction of the learned structured data through experiments. View Full-Text
Keywords: VAE; deep learning; 3D geometry; graph data; generation model VAE; deep learning; 3D geometry; graph data; generation model
Show Figures

Figure 1

MDPI and ACS Style

Park, S.; Kim, H. FaceVAE: Generation of a 3D Geometric Object Using Variational Autoencoders. Electronics 2021, 10, 2792. https://doi.org/10.3390/electronics10222792

AMA Style

Park S, Kim H. FaceVAE: Generation of a 3D Geometric Object Using Variational Autoencoders. Electronics. 2021; 10(22):2792. https://doi.org/10.3390/electronics10222792

Chicago/Turabian Style

Park, Sungsoo, and Hyeoncheol Kim. 2021. "FaceVAE: Generation of a 3D Geometric Object Using Variational Autoencoders" Electronics 10, no. 22: 2792. https://doi.org/10.3390/electronics10222792

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop