One Shot Photometric Stereo from Reflectance Classification

Toshiya Kawabata, Fumihiko Sakaue, Jun Sato

2016

Abstract

3D reconstruction of object shape is one of the most important problem in the field of computer vision. Especially, estimation of normal orientation of object surface is useful for photo-realistic image rendering. For this estimation, the photometric stereo is often used. However, it requires multiple images taken under different lighting conditions in the same pose, and thus, we cannot apply it to moving objects in general. In this paper, we propose a one-shot photometric stereo for estimating surface normal of moving objects with arbitrary textures. In our method, we estimate surface orientation and reflectance property simultaneously. For this objective, reflectance data set is used for decreasing DoF (Degree of Freedom) of estimation. In addition, we classify reflectance property of an input image into limited number of classes. By using the prior knowledge, our method can estimate surface orientation and reflectance property, even if input information is not sufficient for the estimation.

References

  1. Agarwal, S., Furukawa, Y., Snavely, N., Simon, I., Curless, B., Seitz, S. M., and Szeliski, R. (2011). Building rome in a day. Commun. ACM, 54(10):105-112.
  2. Anderson, R., Stenger, B., and Cipolla, R. (2011). Color photometric stereo for multicolored surfaces. In Proc. ICCV2011, pages 2182-2189.
  3. Brostow, G., Hernandez, C., Vogiatzis, G., Stenger, B., and Cipolla, R. (2011). Video normals from colored lights. Trans. PAMI, 33(10):2104-2114.
  4. Chen, C., Vauero, D., and Turk, M. (2011). Illumination demultiplexing from a single image. In Proc. ICCV2011, pages 17-24.
  5. Fyffe, G., Yu, X., and Debevec, P. (2011). Single-shot photometric stereo by spectral multiplexing. In Proc. International Conference on Computational Photography, pages 1-6.
  6. Hartley, R. and Zisserman, A. (2000). Multiple View Geometry in Computer Vision. Cambridge University Press.
  7. Kohonen, O., Parkkinen, J., Jaaskelaienen, T., and Parkkinen, J. (2005). Databases for spectral color science. In 10th Congress of the International Colour Association, pages 1649-1652.
  8. Newcombe, R., Lovegrove, S., and Davison, A. (2011). Dtam: Dense tracking and mapping in real-time. In Proc. ICCV2011, pages 2320-2327.
Download


Paper Citation


in Harvard Style

Kawabata T., Sakaue F. and Sato J. (2016). One Shot Photometric Stereo from Reflectance Classification . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 618-625. DOI: 10.5220/0005718406180625


in Bibtex Style

@conference{visapp16,
author={Toshiya Kawabata and Fumihiko Sakaue and Jun Sato},
title={One Shot Photometric Stereo from Reflectance Classification},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016)},
year={2016},
pages={618-625},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005718406180625},
isbn={978-989-758-175-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 3: VISAPP, (VISIGRAPP 2016)
TI - One Shot Photometric Stereo from Reflectance Classification
SN - 978-989-758-175-5
AU - Kawabata T.
AU - Sakaue F.
AU - Sato J.
PY - 2016
SP - 618
EP - 625
DO - 10.5220/0005718406180625