A Convex Framework for High Resolution 3D Reconstruction

Min Li, Changyu Diao, Song Lv, Dongming Lu

2015

Abstract

We present a convex framework to acquire high resolution surfaces. It is typical to couple a structure-light setup and a photometric method to reconstruct a high resolution 3D surface. Previous methods often get stuck in a local minima for the appearance of occasional outliers. To address this issue, we develop a convex variational model by incorporating a total variation (TV) regularization term with a data term to generate the surface. Through relaxing the model to an equivalent high dimensional variational problem, we obtain a global minimizer of the proposed problem. Results on both synthetic and real-world data show an excellent performance by utilizing our convex variational model.

Paper Citation

in Harvard Style

Li M., Diao C., Lv S. and Lu D. (2015). A Convex Framework for High Resolution 3D Reconstruction . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-091-8, pages 317-324. DOI: 10.5220/0005306503170324

in Bibtex Style

@conference{visapp15,
author={Min Li and Changyu Diao and Song Lv and Dongming Lu},
title={A Convex Framework for High Resolution 3D Reconstruction},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={317-324},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005306503170324},
isbn={978-989-758-091-8},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2015)
TI - A Convex Framework for High Resolution 3D Reconstruction
SN - 978-989-758-091-8
AU - Li M.
AU - Diao C.
AU - Lv S.
AU - Lu D.
PY - 2015
SP - 317
EP - 324
DO - 10.5220/0005306503170324