Proceedings of the 3rd International Conference on Computer Science and Service System

An Improved Patch based Multi-View Stereo (PMVS) Algorithm

Authors
Lichun Wang, Ran Chen, Dehui Kong
Corresponding Author
Lichun Wang
Available Online June 2014.
DOI
10.2991/csss-14.2014.3How to use a DOI?
Keywords
Multi-view reconstruction; PMVS; quasi-dense matching
Abstract

Multi-view based reconstruction is always focused in computer graphics and many excellent algorithms have been reported these years. According to Middlebury benchmark, PMVS(Patch based Multi-View Stereo) outperforms all the other submitted algorithms [1]. In this paper, we propose an improved PMVS algorithm based on quasi-dense matching to save time cost of the original algorithm. Improved algorithm reduces running time for patch expansion through building a quasi-dense set of initial patches and depresses time complexity of the algorithm. The experiments demonstrate effectiveness of improved algorithm.

Copyright
© 2014, 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)

Volume Title
Proceedings of the 3rd International Conference on Computer Science and Service System
Series
Advances in Intelligent Systems Research
Publication Date
June 2014
ISBN
10.2991/csss-14.2014.3
ISSN
1951-6851
DOI
10.2991/csss-14.2014.3How to use a DOI?
Copyright
© 2014, 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/).

Cite this article

TY  - CONF
AU  - Lichun Wang
AU  - Ran Chen
AU  - Dehui Kong
PY  - 2014/06
DA  - 2014/06
TI  - An Improved Patch based Multi-View Stereo (PMVS) Algorithm
BT  - Proceedings of the 3rd International Conference on Computer Science and Service System
PB  - Atlantis Press
SP  - 9
EP  - 12
SN  - 1951-6851
UR  - https://doi.org/10.2991/csss-14.2014.3
DO  - 10.2991/csss-14.2014.3
ID  - Wang2014/06
ER  -