Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
EUROGRAPHICS 2007 / P. Cignoni and J. Sochor Short Papers Enforcing Scene Constraints In Single View Reconstruction
 

Summary: EUROGRAPHICS 2007 / P. Cignoni and J. Sochor Short Papers
Enforcing Scene Constraints In Single View Reconstruction
Manolis I. A. Lourakis and Antonis A. Argyros
Institute of Computer Science, Foundation for Research and Technology - Hellas
Vassilika Vouton, P.O.Box 1385, GR 711 10, Heraklion, Crete, Greece
email: {lourakis | argyros}@ics.forth.gr
Abstract
Three-dimensional reconstruction from a single view is an under-constrained process that relies critically upon the
availability of prior knowledge about the imaged scene. This knowledge is assumed to be supplied by a user in the
form of geometric constraints such as coplanarity, parallelism, perpendicularity, etc, based on his/her interpreta-
tion of the scene. In the presence of noise, however, most of the existing methods yield reconstructions that only
approximately satisfy the supplied geometric constraints. This paper proposes a novel single view reconstruction
method that provides reconstructions which exactly satisfy all user-supplied constraints. This is achieved by first
obtaining a preliminary reconstruction and then refining it in an extendable, constrained optimization framework.
Categories and Subject Descriptors (according to ACM CCS): I.3.5 [Computational Geometry and Object Model-
ing]: Geometric algorithms, languages, and systems I.2.10 [Vision and Scene Understanding]: 3D/stereo scene
analysis
1. Introduction
Image-based modeling (IBM) constitutes an attractive
paradigm for generating photorealistic 3D models directly

  

Source: Argyros, Antonis - Foundation of Research and Technology, Hellas & Department of Computer Science, University of Crete
Trahanias, Panos - Institute of Computer Science, Foundation of Research and Technology, Hellas

 

Collections: Computer Technologies and Information Sciences