RENDERING VIRTUAL OBJECTS INTO REAL SCENE BY USING A DIFFUSE SPHERE

Yuji Kanda, Fumihiko Sakaue, Jun Sato, Kazuhisa Ishimaru, Masayuki Imanishi

2012

Abstract

In this paper, we propose an efficient method for rendering virtual objects into real scene images. We put a diffuse sphere into the scene as a reference object, and use the direct relationship between the intensity of the diffuse sphere and the intensity of virtual objects for rendering the virtual objects in images. We also generate shadows of the virtual objects by using shadows of the reference sphere. As a result, arbitrary virtual objects and their shadows can be rendered quite efficiently from a single diffuse sphere put in the scene. The proposed method is tested in real image experiments, and evaluated quantitatively comparing with the existing method.

References

  1. Debevec, P. (1998). Rendering synthetic objects into real scenes: Bridging traditional and image-based graphics with global illumination and high dynamic range photography. In Proc. SIGGRAPH 98, pages 189-198.
  2. Kanbara, M. and Yokoya, N. (2004). Shadow representation for augmented reality by estimating light environment and shape of real scene. In Proc. MIRU, volume 2, pages 247-252.
  3. Marschner, S. and Greenberg, D. (1997). Inverse lighting for photography. In Proc. Color Imaging Conference, pages 262-265.
  4. Sato, I., Sato, Y., and Ikeuchi, K. (2003). Illumination from shadows. IEEE Transaction on Pattern Analysis and Machine Intelligence, 25(3):290-300.
  5. Takai, T., Nishimura, K., Maki, A., and Matsuyama, T. (2004). Difference sphere: an approach to near light source estimation. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 98-105.
  6. Weber, M. and Cipolla, R. (2001). A practical method for estimation of point light sources. In Proc. British Machine Vision Conference, pages 471-480.
  7. Wei, J. (2003). Robust recovery of multiple light source based on local light source constant constraint. Pattern Recognition Letters, 24(1-3):159-172.
  8. Zhang, Y. and Yang, Y. (2001). Multiple illuminant direction detection with application to image synthesis. IEEE Transaction on Pattern Analysis and Machine Intelligence, 23(8):915-920.
Download


Paper Citation


in Harvard Style

Kanda Y., Sakaue F., Sato J., Ishimaru K. and Imanishi M. (2012). RENDERING VIRTUAL OBJECTS INTO REAL SCENE BY USING A DIFFUSE SPHERE . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012) ISBN 978-989-8565-03-7, pages 279-285. DOI: 10.5220/0003850202790285


in Bibtex Style

@conference{visapp12,
author={Yuji Kanda and Fumihiko Sakaue and Jun Sato and Kazuhisa Ishimaru and Masayuki Imanishi},
title={RENDERING VIRTUAL OBJECTS INTO REAL SCENE BY USING A DIFFUSE SPHERE},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)},
year={2012},
pages={279-285},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003850202790285},
isbn={978-989-8565-03-7},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2012)
TI - RENDERING VIRTUAL OBJECTS INTO REAL SCENE BY USING A DIFFUSE SPHERE
SN - 978-989-8565-03-7
AU - Kanda Y.
AU - Sakaue F.
AU - Sato J.
AU - Ishimaru K.
AU - Imanishi M.
PY - 2012
SP - 279
EP - 285
DO - 10.5220/0003850202790285