Multiview Point Cloud Filtering for Spatiotemporal Consistency
Robert Skupin, Thilo Borgmann, Thomas Sikora
2014
Abstract
This work presents algorithms to resample and filter point cloud data reconstructed from multiple cameras and multiple time instants. In an initial resampling stage, a voxel or a surface mesh based approach resamples the point cloud data into a common sampling grid. Subsequently, the resampled data undergoes a filtering stage based on clustering to remove artifacts and achieve spatiotemporal consistency across cameras and time instants. The presented algorithms are evaluated in a view synthesis scenario. Results show that view synthesis with enhanced depth maps as produced by the algorithms leads to less artifacts than synthesis with the original source data.
DownloadPaper Citation
in Harvard Style
Skupin R., Borgmann T. and Sikora T. (2014). Multiview Point Cloud Filtering for Spatiotemporal Consistency . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-009-3, pages 531-538. DOI: 10.5220/0004681805310538
in Bibtex Style
@conference{visapp14,
author={Robert Skupin and Thilo Borgmann and Thomas Sikora},
title={Multiview Point Cloud Filtering for Spatiotemporal Consistency},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={531-538},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004681805310538},
isbn={978-989-758-009-3},
}
in EndNote Style
TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2014)
TI - Multiview Point Cloud Filtering for Spatiotemporal Consistency
SN - 978-989-758-009-3
AU - Skupin R.
AU - Borgmann T.
AU - Sikora T.
PY - 2014
SP - 531
EP - 538
DO - 10.5220/0004681805310538