Super-Resolution 3D Reconstruction from Multiple Cameras

Tomoaki Nonome, Fumihiko Sakaue, Jun Sato

Abstract

In this paper, we propose a novel method for reconstructing high resolution 3D structure and texture of the scene. In the image processing, it is known that image super-resolution is possible from multiple low resolution images. In this paper, we extend the image super-resolution into 3D space, and show that it is possible to recover high resolution 3D structure and high resolution texture of the scene from low resolution images taken at different viewpoints. The experimental results from real and synthetic images show the efficiency of the proposed method.

Download


Paper Citation


in Harvard Style

Nonome T., Sakaue F. and Sato J. (2018). Super-Resolution 3D Reconstruction from Multiple Cameras.In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, ISBN 978-989-758-290-5, pages 481-486. DOI: 10.5220/0006718304810486


in Bibtex Style

@conference{visapp18,
author={Tomoaki Nonome and Fumihiko Sakaue and Jun Sato},
title={Super-Resolution 3D Reconstruction from Multiple Cameras},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,},
year={2018},
pages={481-486},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006718304810486},
isbn={978-989-758-290-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP,
TI - Super-Resolution 3D Reconstruction from Multiple Cameras
SN - 978-989-758-290-5
AU - Nonome T.
AU - Sakaue F.
AU - Sato J.
PY - 2018
SP - 481
EP - 486
DO - 10.5220/0006718304810486