Deformable Surface 3D Reconstruction from Monocular Images

Being able to recover the shape of 3D deformable surfaces from a single video stream would make it possible to field reconstruction systems that run on widely available hardware without requiring specialized devices. However, because many different 3D shapes can have virtually the same projection, s...

Descripción completa

Detalles Bibliográficos
Autores principales: Salzmann, Matthieu, Fua, Pascal
Lenguaje:eng
Publicado: Morgan & Claypool Publishers 2010
Materias:
Computing and Computers
Acceso en línea:http://cds.cern.ch/record/1486589
_version_ 1780926152783691776
author Salzmann, Matthieu
Fua, Pascal
author_facet Salzmann, Matthieu
Fua, Pascal
author_sort Salzmann, Matthieu
collection CERN
description Being able to recover the shape of 3D deformable surfaces from a single video stream would make it possible to field reconstruction systems that run on widely available hardware without requiring specialized devices. However, because many different 3D shapes can have virtually the same projection, such monocular shape recovery is inherently ambiguous. In this survey, we will review the two main classes of techniques that have proved most effective so far: The template-based methods that rely on establishing correspondences with a reference image in which the shape is already known, and non-rig
id cern-1486589
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2010
publisher Morgan & Claypool Publishers
record_format invenio
spelling cern-14865892021-04-22T00:16:51Zhttp://cds.cern.ch/record/1486589engSalzmann, MatthieuFua, PascalDeformable Surface 3D Reconstruction from Monocular ImagesComputing and ComputersBeing able to recover the shape of 3D deformable surfaces from a single video stream would make it possible to field reconstruction systems that run on widely available hardware without requiring specialized devices. However, because many different 3D shapes can have virtually the same projection, such monocular shape recovery is inherently ambiguous. In this survey, we will review the two main classes of techniques that have proved most effective so far: The template-based methods that rely on establishing correspondences with a reference image in which the shape is already known, and non-rigMorgan & Claypool Publishersoai:cds.cern.ch:14865892010
spellingShingle Computing and Computers
Salzmann, Matthieu
Fua, Pascal
Deformable Surface 3D Reconstruction from Monocular Images
title Deformable Surface 3D Reconstruction from Monocular Images
title_full Deformable Surface 3D Reconstruction from Monocular Images
title_fullStr Deformable Surface 3D Reconstruction from Monocular Images
title_full_unstemmed Deformable Surface 3D Reconstruction from Monocular Images
title_short Deformable Surface 3D Reconstruction from Monocular Images
title_sort deformable surface 3d reconstruction from monocular images
topic Computing and Computers
url http://cds.cern.ch/record/1486589
work_keys_str_mv AT salzmannmatthieu deformablesurface3dreconstructionfrommonocularimages
AT fuapascal deformablesurface3dreconstructionfrommonocularimages

Ejemplares similares