Abstract

We present a method with which to recover the intrinsic shading and reflectance characteristics of multicolored three-dimensional objects in a single image, with which realistic new scenes can be synthesized. A color watershed algorithm, which is based on a regularized dichromatic fitting error, is proposed for robust image segmentation. For shading recovery in small regions, a weighted interpolation is employed, whereas in large regions the reflectance and shading are calculated based on the assumption of gradual shape variation. It is demonstrated that the proposed method is promising and can be applied in image simulation.

© 2005 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. Y. Sando, M. Itoh, and T. Yatagai, Opt. Lett. 28, 2518 (2003).
    [CrossRef] [PubMed]
  2. B. V. Funt, M. S. Drew, and M. Brockington, in ECCV-92: Second European Conference on Computer Vision, G. Sandini, ed. (Springer-Verlag, 1992), pp. 124–132.
  3. M. F. Tappen, W. T. Freeman, and E. H. Adelson, in Advances in Neural Information Processing Systems 15: Proceedings of the 2002 Conference, S. Becker, S. Thrun, and K. Obermayer, eds. (MIT Press, 2003), p. 1343.
  4. Y. L. Tian and H. T. Tsui, J. Opt. Soc. Am. A 14, 397 (1997).
    [CrossRef]
  5. S. A. Shafer, Color Res. Appl. 10, 210 (1985).
    [CrossRef]
  6. J. H. Xin and H. L. Shen, J. Opt. Soc. Am. A 21, 713 (2004).
    [CrossRef]
  7. H. L. Shen and J. H. Xin, Appl. Opt. 44, 1969 (2005).
    [CrossRef] [PubMed]
  8. G. J. Klinker, S. A. Shafer, and T. Kanade, Int. J. Comput. Vis. 4, 7 (1990).
    [CrossRef]
  9. L. Vincent and P. Soille, IEEE Trans. Pattern Anal. Mach. Intell. 13, 583 (1991).
    [CrossRef]

2005 (1)

2004 (1)

2003 (1)

1997 (1)

1991 (1)

L. Vincent and P. Soille, IEEE Trans. Pattern Anal. Mach. Intell. 13, 583 (1991).
[CrossRef]

1990 (1)

G. J. Klinker, S. A. Shafer, and T. Kanade, Int. J. Comput. Vis. 4, 7 (1990).
[CrossRef]

1985 (1)

S. A. Shafer, Color Res. Appl. 10, 210 (1985).
[CrossRef]

Adelson, E. H.

M. F. Tappen, W. T. Freeman, and E. H. Adelson, in Advances in Neural Information Processing Systems 15: Proceedings of the 2002 Conference, S. Becker, S. Thrun, and K. Obermayer, eds. (MIT Press, 2003), p. 1343.

Brockington, M.

B. V. Funt, M. S. Drew, and M. Brockington, in ECCV-92: Second European Conference on Computer Vision, G. Sandini, ed. (Springer-Verlag, 1992), pp. 124–132.

Drew, M. S.

B. V. Funt, M. S. Drew, and M. Brockington, in ECCV-92: Second European Conference on Computer Vision, G. Sandini, ed. (Springer-Verlag, 1992), pp. 124–132.

Freeman, W. T.

M. F. Tappen, W. T. Freeman, and E. H. Adelson, in Advances in Neural Information Processing Systems 15: Proceedings of the 2002 Conference, S. Becker, S. Thrun, and K. Obermayer, eds. (MIT Press, 2003), p. 1343.

Funt, B. V.

B. V. Funt, M. S. Drew, and M. Brockington, in ECCV-92: Second European Conference on Computer Vision, G. Sandini, ed. (Springer-Verlag, 1992), pp. 124–132.

Itoh, M.

Kanade, T.

G. J. Klinker, S. A. Shafer, and T. Kanade, Int. J. Comput. Vis. 4, 7 (1990).
[CrossRef]

Klinker, G. J.

G. J. Klinker, S. A. Shafer, and T. Kanade, Int. J. Comput. Vis. 4, 7 (1990).
[CrossRef]

Sando, Y.

Shafer, S. A.

G. J. Klinker, S. A. Shafer, and T. Kanade, Int. J. Comput. Vis. 4, 7 (1990).
[CrossRef]

S. A. Shafer, Color Res. Appl. 10, 210 (1985).
[CrossRef]

Shen, H. L.

Soille, P.

L. Vincent and P. Soille, IEEE Trans. Pattern Anal. Mach. Intell. 13, 583 (1991).
[CrossRef]

Tappen, M. F.

M. F. Tappen, W. T. Freeman, and E. H. Adelson, in Advances in Neural Information Processing Systems 15: Proceedings of the 2002 Conference, S. Becker, S. Thrun, and K. Obermayer, eds. (MIT Press, 2003), p. 1343.

Tian, Y. L.

Tsui, H. T.

Vincent, L.

L. Vincent and P. Soille, IEEE Trans. Pattern Anal. Mach. Intell. 13, 583 (1991).
[CrossRef]

Xin, J. H.

Yatagai, T.

Appl. Opt. (1)

Color Res. Appl. (1)

S. A. Shafer, Color Res. Appl. 10, 210 (1985).
[CrossRef]

IEEE Trans. Pattern Anal. Mach. Intell. (1)

L. Vincent and P. Soille, IEEE Trans. Pattern Anal. Mach. Intell. 13, 583 (1991).
[CrossRef]

Int. J. Comput. Vis. (1)

G. J. Klinker, S. A. Shafer, and T. Kanade, Int. J. Comput. Vis. 4, 7 (1990).
[CrossRef]

J. Opt. Soc. Am. A (2)

Opt. Lett. (1)

Other (2)

B. V. Funt, M. S. Drew, and M. Brockington, in ECCV-92: Second European Conference on Computer Vision, G. Sandini, ed. (Springer-Verlag, 1992), pp. 124–132.

M. F. Tappen, W. T. Freeman, and E. H. Adelson, in Advances in Neural Information Processing Systems 15: Proceedings of the 2002 Conference, S. Becker, S. Thrun, and K. Obermayer, eds. (MIT Press, 2003), p. 1343.

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (3)

Fig. 1
Fig. 1

(Color online) Results of segmentation of the color watershed algorithm on (a) the image of a toy train with parameters (b) λ = 0 and (d) λ = 1 . (c), (e) Details of the rectangles in (b) and (d), respectively.

Fig. 2
Fig. 2

(Color online) Experimental results for the image of a cup: (a) original image; (b), (e) shading images recovered with the proposed method and with Tappen’s method, respectively; (c), (f) reflectance images recovered with the proposed method and with Tappen’s method, respectively; (d) new image synthesized by the proposed method.

Fig. 3
Fig. 3

(Color online) Experimental results for a toy image: (a) original image, (b) shading image, (c) reflectance image, (d) synthesized new image.

Equations (4)

Equations on this page are rendered with MathJax. Learn more.

V p = α p K + β p H = M c p ,
h p = arctan [ 3 ( V 2 p V 1 p ) 2 V 3 p V 1 p V 2 p ] = arctan [ 3 ( K 2 p K 1 p ) 2 K 3 p K 1 p K 2 p ] .
d i p = V p M i ( M i + V p ) + λ [ M i + V p ] 1 α ¯ ,
α 0 p K n + β 0 p H = V n , i p .

Metrics