Primitive-based Surface Regularization for Urban 3D Reconstruction
Thomas Holzmann, Martin Oswald, Marc Pollefeys, Friedrich Fraundorfer and Horst Bischof
Abstract
We propose a method for urban 3D reconstruction that is a hybrid between a volumetric 3D reconstruction approach and a plane fitting approach in order to obtain a denoised
and compact representation of the scene. In our hybrid approach, a single global optimization, using visibility as main information, defines whether the final reconstructed
surface should align with a detected plane or rather follow the details of the input data.
Our method is based on an established tetrahedral occupancy labeling approach which
we taylor for urban reconstruction by adding the possibility to favor an alignment of
the surface with detected planes. We further add novel regularization terms that favor
Manhattan-like structures and which allow to control the level of detail of the output
model.
Session
Posters
Files
Paper (PDF)
Supplementary (PDF)
DOI
10.5244/C.31.177
https://dx.doi.org/10.5244/C.31.177
Citation
Thomas Holzmann, Martin Oswald, Marc Pollefeys, Friedrich Fraundorfer and Horst Bischof. Primitive-based Surface Regularization for Urban 3D Reconstruction. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 177.1-177.14. BMVA Press, September 2017.
Bibtex
@inproceedings{BMVC2017_177,
title={Primitive-based Surface Regularization for Urban 3D Reconstruction},
author={Thomas Holzmann, Martin Oswald, Marc Pollefeys, Friedrich Fraundorfer and Horst Bischof},
year={2017},
month={September},
pages={177.1-177.14},
articleno={177},
numpages={14},
booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
publisher={BMVA Press},
editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
doi={10.5244/C.31.177},
isbn={1-901725-60-X},
url={https://dx.doi.org/10.5244/C.31.177}
}