Indoor Scene Reconstruction using Primitive-driven Space Partitioning and Graph-cut

Oesau, Sven; Lafarge, Florent; Alliez, Pierre

Indoor Scene Reconstruction using Primitive-driven Space Partitioning and Graph-cut

Files

009-012.pdf (1.33 MB)

Date

2013

Authors

Oesau, Sven
Lafarge, Florent
Alliez, Pierre

Publisher

The Eurographics Association

Abstract

We present a method for automatic reconstruction of permanent structures of indoor scenes, such as walls, floors and ceilings, from raw point clouds acquired by laser scanners. Our approach employs graph-cut to solve an inside/outside labeling of a space decomposition. To allow for an accurate reconstruction the space decomposition is aligned with permanent structures. A Hough Transform is applied for extracting the wall directions while allowing a flexible reconstruction of scenes. The graph-cut formulation takes into account data consistency through an inside/outside prediction for the cells of the space decomposition by stochastic ray casting, while favoring low geometric complexity of the model. Our experiments produces watertight reconstructed models of multi-level buildings and complex scenes.

        @inproceedings{:10.2312/UDMV/UDMV13/009-012
,
booktitle = {Eurographics Workshop on Urban Data Modelling and Visualisation
},
editor = {Vincent Tourre and Gonzalo Besuievsky
},
title = {{Indoor Scene Reconstruction using Primitive-driven Space Partitioning and Graph-cut
}},
author = {Oesau, Sven and 
Lafarge, Florent and 
Alliez, Pierre
},
year = {2013
},
publisher = {The Eurographics Association
},
ISSN = {2307-8251
},
ISBN = {978-3-905674-46-0
},
DOI = {/10.2312/UDMV/UDMV13/009-012
}
}