Recovering 3D Structure of Multilayer Transparent Objects from Multi-view Ray Tracing

Atsunori Maeda, Fumihiko Sakaue, Jun Sato

2017

Abstract

3D reconstruction of object shape is one of the most important problems in the field of computer vision. Although many methods have been proposed up to now, the 3D reconstruction of transparent objects is still a very difficult unsolved problem. In particular, if the transparent objects have multiple layers with different refraction properties, the recovery of the 3D structure of transparent objects is quite difficult. In this paper, we propose a method for recovering the 3D structure of multilayer transparent objects. For this objective we introduce a new representation of 3D space by using a boxel with refraction properties, and recovering the refraction properties of each boxel by using the ray tracing. The efficiency of the proposed method is shown by some preliminary experiments.

References

  1. Agarwal, S., Snavely, N., Simon, I., Seitz, S., and Szeliski, R. (2009). Building rome in a day. In Proc. ICCV.
  2. Ding, Y., Li, F., Ji, Y., and Yu, J. (2011). Dynamic fluid surface acquisition using a camera array. In Proc. ICCV.
  3. Heinly, J., Schonberger, J., Dunn, E., and Frahm, J. (2015). Reconstructing the world in six days. In Proc. Conference on Computer Vision and Pattern Recognition, pages 3287-3295.
  4. Miyazaki, D. and Ikeuchi, K. (2007). Shape estimation of transparent objects by using inverse polarization ray tracing. Trans. PAMI, pages 2018?-2030.
  5. Qian, Y., Gong, G., and Yang, Y. (2016). 3d reconstruction of transparent objects with position-normal consistency. In Proc. Conference on Computer Vision and Pattern Recognition.
  6. Shan, Q., Agarwal, S., and Curless, B. (2012). Refractive height fields from single and multiple images. In Proc. Conference on Computer Vision and Pattern Recognition.
  7. Tsai, C., Veeraraghavan, A., and Sankaranarayanan, A. (2015). What does a light ray reveal about a transparent object? In Proc. ICIP.
  8. Wetzstein, G., Roodnick, D., Heidrich, W., and Raskar, R. (2011). Refractive shape from light field distortion. In Proc. ICCV.
Download


Paper Citation


in Harvard Style

Maeda A., Sakaue F. and Sato J. (2017). Recovering 3D Structure of Multilayer Transparent Objects from Multi-view Ray Tracing . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-227-1, pages 523-527. DOI: 10.5220/0006265905230527


in Bibtex Style

@conference{visapp17,
author={Atsunori Maeda and Fumihiko Sakaue and Jun Sato},
title={Recovering 3D Structure of Multilayer Transparent Objects from Multi-view Ray Tracing},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={523-527},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006265905230527},
isbn={978-989-758-227-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017)
TI - Recovering 3D Structure of Multilayer Transparent Objects from Multi-view Ray Tracing
SN - 978-989-758-227-1
AU - Maeda A.
AU - Sakaue F.
AU - Sato J.
PY - 2017
SP - 523
EP - 527
DO - 10.5220/0006265905230527