Multi-View Images 3D Reconstruction based on Spatial Geometric Constraint

DOI

10.2991/wartia-16.2016.256How to use a DOI?

Keywords

3D Reconstruction, PMVS, Spatial Geometric Constraint

Abstract

The PMVS algorithm due to lacking of geometric constraint during expanding spare points to dense points cloud, resulting in error vertices which are generated from Poisson surface reconstruction. In This paper we consider facets around the expanding one at the same time, then detect the outlier vertices of triangle meshes according to the k Nearest Neighbor and remove outliers. Experimental results demonstrate the effectiveness and accuracy of the algorithm.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Haibo Liu
PY  - 2016/05
DA  - 2016/05
TI  - Multi-View Images 3D Reconstruction based on Spatial Geometric Constraint
BT  - Proceedings of the 2016 2nd Workshop on Advanced Research and Technology in Industry Applications
PB  - Atlantis Press
SP  - 1215
EP  - 1218
SN  - 2352-5401
UR  - https://doi.org/10.2991/wartia-16.2016.256
DO  - 10.2991/wartia-16.2016.256
ID  - Liu2016/05
ER  -