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

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 limite...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sungsoo Park, Hyeoncheol Kim
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	VAE deep learning 3D geometry graph data generation model Electronics TK7800-8360
Acceso en línea:	https://doaj.org/article/c12fe31ef7e1468087945302a3b6ee0e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c12fe31ef7e1468087945302a3b6ee0e
record_format	dspace
spelling	oai:doaj.org-article:c12fe31ef7e1468087945302a3b6ee0e2021-11-25T17:24:41ZFaceVAE: Generation of a 3D Geometric Object Using Variational Autoencoders10.3390/electronics102227922079-9292https://doaj.org/article/c12fe31ef7e1468087945302a3b6ee0e2021-11-01T00:00:00Zhttps://www.mdpi.com/2079-9292/10/22/2792https://doaj.org/toc/2079-9292Deep 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.Sungsoo ParkHyeoncheol KimMDPI AGarticleVAEdeep learning3D geometrygraph datageneration modelElectronicsTK7800-8360ENElectronics, Vol 10, Iss 2792, p 2792 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	VAE deep learning 3D geometry graph data generation model Electronics TK7800-8360
spellingShingle	VAE deep learning 3D geometry graph data generation model Electronics TK7800-8360 Sungsoo Park Hyeoncheol Kim FaceVAE: Generation of a 3D Geometric Object Using Variational Autoencoders
description	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.
format	article
author	Sungsoo Park Hyeoncheol Kim
author_facet	Sungsoo Park Hyeoncheol Kim
author_sort	Sungsoo Park
title	FaceVAE: Generation of a 3D Geometric Object Using Variational Autoencoders
title_short	FaceVAE: Generation of a 3D Geometric Object Using Variational Autoencoders
title_full	FaceVAE: Generation of a 3D Geometric Object Using Variational Autoencoders
title_fullStr	FaceVAE: Generation of a 3D Geometric Object Using Variational Autoencoders
title_full_unstemmed	FaceVAE: Generation of a 3D Geometric Object Using Variational Autoencoders
title_sort	facevae: generation of a 3d geometric object using variational autoencoders
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/c12fe31ef7e1468087945302a3b6ee0e
work_keys_str_mv	AT sungsoopark facevaegenerationofa3dgeometricobjectusingvariationalautoencoders AT hyeoncheolkim facevaegenerationofa3dgeometricobjectusingvariationalautoencoders
_version_	1718412434679529472

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

Ejemplares similares