Shape from Multi-view Images based on Image Generation Consistency

Kousuke Wakabayashi, Norio Tagawa, Kan Okubo

2013

Abstract

There are various and a lot of depth recovery methods have been studied, but a discussion about an unification of individual methods is expected not to be enough yet. In this study, we argue that the importance and the necessity of an image generation consistency. Various clues including binocular disparity, motion parallax, texture, shading and so on can be effectively used for depth recovery for the case where each or some of those are completely performed. However, in general, those clues without shading cause ideal and simplified constraints, and for several cases those clues without shading are suitable for obtaining initial depth values for the unification algorithm based on an image generation consistency. On the other hand, shading indicates a strict characteristics for image generation and should be used for the key principle for the unification. Based on the above strategy, as a first step of our scheme, through a simple problem with two-views, the unification of binocular disparity and shading without explicit disparity detection is examined based on an image generation consistency, and simple evaluation results are shown by simulations.

References

  1. Brooks, M. J. and Horn, B. K. P. (1985). Shape and source from shading. In proc. Int. Joint Conf. Art. Intell., pages 18-23.
  2. Hayakawa, H., Nishida, S., Wada, Y., and Kawato, M. (1994). A computational model for shape estimation by integration of shading and edge information. Neural Networks, 7(8):1193-1209.
  3. Horn, B. K. P. (1990). Height and gradient from shading. Int. J. Computer Vision, 5(1):37-75.
  4. Lazaros, N., Sirakoulis, G. C., and Gasteratos, A. (2008). Review of stereo vision algorithm: from software to hardware. Int. J. Optomechatronics, 5(4):435-462.
  5. Leclerc, Y. G. and Bobick, A. F. (1991). The direct computation of height from shading. In proc. CVPR 7891, pages 552-558.
  6. Maki, A., Watanabe, M., and Wiles, C. (2002). Geotensity: combination motion and lighting for 3d surface reconstrcution. Int. Journal of Comput. Vision, 48(2):75- 90.
  7. Phong, B. T. (1975). Illumination for computer generated pictures. Communication of the ACM, 18(6):311-317.
  8. Poggio, T., Gamble, E. B., and Little, J. J. (1988). Parallel integration of vision modules. Science, 242:43-440.
  9. Samaras, D., Metaxas, D., Fua, P., and Leclerc, Y. G. (2000). Variable albedo surface reconstruction from stereo and shape from shading. In proc. Int. Conf. CVPR, volume 1, pages 480-487.
  10. S.A.Shafer (1985). Using color to separate reflection components. Color Research and Application, 10(4):210- 218.
  11. Szeliski, R. (1991). Fast shape from shading. CVGIP: Image Understanding, 53(2):129-153.
  12. Terzopoulos, D. (1983). Multilevel computational processes for visual surface reconstruction. Computer Vision, Graphics, and Image Processing, 24:52-96.
  13. Wakabayashi, K., Tagawa, N., and Okubo, K. (2012). Direct computation of depth from shading for perspective projection. In proc. Int. Conf. Comput. Vision, Theory and Applications, pages 445-448.
  14. Zhang, R., Tsai, P.-S., Cryer, J. E., and Shah, M. (1999). Shape from shading: A survey. IEEE Trans. PAMI, 21(8):690-706.
Download


Paper Citation


in Harvard Style

Wakabayashi K., Tagawa N. and Okubo K. (2013). Shape from Multi-view Images based on Image Generation Consistency . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-48-8, pages 334-340. DOI: 10.5220/0004345203340340


in Bibtex Style

@conference{visapp13,
author={Kousuke Wakabayashi and Norio Tagawa and Kan Okubo},
title={Shape from Multi-view Images based on Image Generation Consistency},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={334-340},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004345203340340},
isbn={978-989-8565-48-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2013)
TI - Shape from Multi-view Images based on Image Generation Consistency
SN - 978-989-8565-48-8
AU - Wakabayashi K.
AU - Tagawa N.
AU - Okubo K.
PY - 2013
SP - 334
EP - 340
DO - 10.5220/0004345203340340