Textured Mesh Generation Using Multi-View and Multi-Source Supervision and Generative Adversarial Networks

This study focuses on reconstructing accurate meshes with high-resolution textures from single images. The reconstruction process involves two networks: a mesh-reconstruction network and a texture-reconstruction network. The mesh-reconstruction network estimates a deformation map, which is used to d...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mingyun Wen, Jisun Park, Kyungeun Cho
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	single image textured mesh reconstruction convolutional neural networks generative adversarial network super-resolution Science Q
Acceso en línea:	https://doaj.org/article/b08f0012ca384ebdb65dcb0499bc9160
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b08f0012ca384ebdb65dcb0499bc9160
record_format	dspace
spelling	oai:doaj.org-article:b08f0012ca384ebdb65dcb0499bc91602021-11-11T18:51:37ZTextured Mesh Generation Using Multi-View and Multi-Source Supervision and Generative Adversarial Networks10.3390/rs132142542072-4292https://doaj.org/article/b08f0012ca384ebdb65dcb0499bc91602021-10-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4254https://doaj.org/toc/2072-4292This study focuses on reconstructing accurate meshes with high-resolution textures from single images. The reconstruction process involves two networks: a mesh-reconstruction network and a texture-reconstruction network. The mesh-reconstruction network estimates a deformation map, which is used to deform a template mesh to the shape of the target object in the input image, and a low-resolution texture. We propose reconstructing a mesh with a high-resolution texture by enhancing the low-resolution texture through use of the super-resolution method. The architecture of the texture-reconstruction network is like that of a generative adversarial network comprising a generator and a discriminator. During the training of the texture-reconstruction network, the discriminator must focus on learning high-quality texture predictions and to ignore the difference between the generated mesh and the actual mesh. To achieve this objective, we used meshes reconstructed using the mesh-reconstruction network and textures generated through inverse rendering to generate pseudo-ground-truth images. We conducted experiments using the 3D-Future dataset, and the results prove that our proposed approach can be used to generate improved three-dimensional (3D) textured meshes compared to existing methods, both quantitatively and qualitatively. Additionally, through our proposed approach, the texture of the output image is significantly improved.Mingyun WenJisun ParkKyungeun ChoMDPI AGarticlesingle image textured mesh reconstructionconvolutional neural networksgenerative adversarial networksuper-resolutionScienceQENRemote Sensing, Vol 13, Iss 4254, p 4254 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	single image textured mesh reconstruction convolutional neural networks generative adversarial network super-resolution Science Q
spellingShingle	single image textured mesh reconstruction convolutional neural networks generative adversarial network super-resolution Science Q Mingyun Wen Jisun Park Kyungeun Cho Textured Mesh Generation Using Multi-View and Multi-Source Supervision and Generative Adversarial Networks
description	This study focuses on reconstructing accurate meshes with high-resolution textures from single images. The reconstruction process involves two networks: a mesh-reconstruction network and a texture-reconstruction network. The mesh-reconstruction network estimates a deformation map, which is used to deform a template mesh to the shape of the target object in the input image, and a low-resolution texture. We propose reconstructing a mesh with a high-resolution texture by enhancing the low-resolution texture through use of the super-resolution method. The architecture of the texture-reconstruction network is like that of a generative adversarial network comprising a generator and a discriminator. During the training of the texture-reconstruction network, the discriminator must focus on learning high-quality texture predictions and to ignore the difference between the generated mesh and the actual mesh. To achieve this objective, we used meshes reconstructed using the mesh-reconstruction network and textures generated through inverse rendering to generate pseudo-ground-truth images. We conducted experiments using the 3D-Future dataset, and the results prove that our proposed approach can be used to generate improved three-dimensional (3D) textured meshes compared to existing methods, both quantitatively and qualitatively. Additionally, through our proposed approach, the texture of the output image is significantly improved.
format	article
author	Mingyun Wen Jisun Park Kyungeun Cho
author_facet	Mingyun Wen Jisun Park Kyungeun Cho
author_sort	Mingyun Wen
title	Textured Mesh Generation Using Multi-View and Multi-Source Supervision and Generative Adversarial Networks
title_short	Textured Mesh Generation Using Multi-View and Multi-Source Supervision and Generative Adversarial Networks
title_full	Textured Mesh Generation Using Multi-View and Multi-Source Supervision and Generative Adversarial Networks
title_fullStr	Textured Mesh Generation Using Multi-View and Multi-Source Supervision and Generative Adversarial Networks
title_full_unstemmed	Textured Mesh Generation Using Multi-View and Multi-Source Supervision and Generative Adversarial Networks
title_sort	textured mesh generation using multi-view and multi-source supervision and generative adversarial networks
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/b08f0012ca384ebdb65dcb0499bc9160
work_keys_str_mv	AT mingyunwen texturedmeshgenerationusingmultiviewandmultisourcesupervisionandgenerativeadversarialnetworks AT jisunpark texturedmeshgenerationusingmultiviewandmultisourcesupervisionandgenerativeadversarialnetworks AT kyungeuncho texturedmeshgenerationusingmultiviewandmultisourcesupervisionandgenerativeadversarialnetworks
_version_	1718431720297988096

Textured Mesh Generation Using Multi-View and Multi-Source Supervision and Generative Adversarial Networks

Ejemplares similares