Publication Details

Fast and Accurate Refinement Method for 3D Reconstruction from Stereo Spherical Images

ŠOLONY Marek, IMRE Evren, ILA Viorela S., POLOK Lukáš, KIM Hansung and ZEMČÍK Pavel. Fast and Accurate Refinement Method for 3D Reconstruction from Stereo Spherical Images. In: Proceedings of the 10th International Conference on Computer Vision Theory and Applications. Berlin: Institute of Electrical and Electronics Engineers, 2015, pp. 1-8. ISBN 978-989-8425-47-8.
Czech title
Rychlá a přesná optimalizační metoda pro 3D rekonstrukci z stereo sférických obrázků
Type
conference paper
Language
english
Authors
Šolony Marek, Ing., PhD. (DCGM FIT BUT)
Imre Evren (USG)
Ila Viorela S., Ing., Ph.D. (DCGM FIT BUT)
Polok Lukáš, Ing. (DCGM FIT BUT)
Kim Hansung (USG)
Zemčík Pavel, prof. Dr. Ing. (DCGM FIT BUT)
Keywords

spherical images registration, 3D reconstruction, graph optimisation, SLAM

Abstract

Realistic 3D models of the environment are beneficial in many fields, from natural or man-made structure inspection and volumetric analysis, to movie-making, in particular, special effects integration to natural scenes.
Spherical cameras are becoming popular in environment modelling because they capture the full surrounding scene visible from the camera location as a consistent seamless image at once.
In this paper, we propose a novel pipeline to obtain fast and accurate 3D reconstructions from spherical images. In order to have a better estimation of the structure, the system integrates a joint camera pose and structure refinement step. This strategy proves to be much faster, yet equally accurate, when compared to the conventional method, registration of a dense point cloud via iterative closest point (ICP). Both methods require an initial estimate for successful convergence. The initial positions of the 3D points are obtained from stereo processing of pair of spherical images with known baseline. The initial positions of the cameras are obtained from a robust wide-baseline matching procedure. The performance and accuracy of the 3D reconstruction pipeline is analysed through extensive tests on several indoor and outdoor datasets.

Published
2015
Pages
1-8
Proceedings
Proceedings of the 10th International Conference on Computer Vision Theory and Applications
Conference
International Conference on Computer Vision Theory and Applications 2015, Berlin, Německo, DE
ISBN
978-989-8425-47-8
Publisher
Institute of Electrical and Electronics Engineers
Place
Berlin, DE
DOI
10.5220/0005310805750583
EID Scopus
2-s2.0-84939557928
BibTeX 
@INPROCEEDINGS{FITPUB10866,
   author = "Marek \v{S}olony and Evren Imre and S. Viorela Ila and Luk\'{a}\v{s} Polok and Hansung Kim and Pavel Zem\v{c}\'{i}k",
   title = "Fast and Accurate Refinement Method for 3D Reconstruction from Stereo Spherical Images",
   pages = "1--8",
   booktitle = " Proceedings of the 10th International Conference on Computer Vision Theory and Applications",
   year = 2015,
   location = "Berlin, DE",
   publisher = "Institute of Electrical and Electronics Engineers",
   ISBN = "978-989-8425-47-8",
   doi = "10.5220/0005310805750583",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/10866"
}
Files
Back to top