Skip to main content
SpringerLink
Log in

Single view compositing with shadows

  • original article
  • Published:
The Visual Computer Aims and scope Submit manuscript

Abstract

In this paper, we describe how geometrically correct and visually realistic shadows may be computed for objects composited into a single view of a target scene. Compared to traditional single view compositing methods, which either do not deal with the shadow effects or manually create the shadows for the composited objects, our approach efficiently utilizes the geometric and photometric constraints extracted from a single target image to synthesize the shadows consistent with the overall target scene for the inserted objects. In particular, we explore (i) the constraints provided by imaged scene structure, e.g. vanishing points of orthogonal directions, for camera calibration and thus explicit determination of the locations of the camera and the light source; (ii) the relatively weaker geometric constraint, the planar homology, that models the imaged shadow relations when explicit camera calibration is not possible; and (iii) the photometric constraints that are required to match the color characteristics of the synthesized shadows with those of the original scene. For each constraint, we demonstrate the working examples followed by our observations. To show the accuracy and the applications of the proposed method, we present the results for a variety of target scenes, including footage from commercial Hollywood movies and 3D video games.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. Agarwala, A., A., Salesin, D.H., Seitz, S.M.: Keyframe-based tracking for rotoscoping and animation. ACM Trans. Graph. 23(3), 584–591 (2004)

  2. Apostoloff, N.E., Fitzgibbon, A.: Bayesian video matting using learnt image priors. In: Proc. IEEE CVPR, pp. 407–414 (2004)

  3. Barrow, H., Tenenbaum, J.: Recovering intrinsic scene character-istics from images. Academic Press (1978)

  4. Cao, X., Shah, M.: Camera calibration and light source estimation from images with shadows. In: Proc. IEEE CVPR, pp. 918–923 (2005)

  5. Caprile, B., Torre, V.: Using vanishing points for camera calibra-tion. Int. J. Comput. Vision 4(2), 127–140 (1990)

    Google Scholar 

  6. Chen, Q., Wu, H., Wada, T.: Camera calibration with two arbitrary coplanar circles. In: Proc. ECCV, pp. 521–532 (2004)

  7. Chuang, Y.: New models and methods for matting and compositing. Ph.D. thesis, University of Washington (2004)

  8. Crow, F.C.: Shadow algorithms for computer graphics. In: Proc. of SIGGRAPH, pp. 242–248 (1977)

  9. Finlayson, G., Drew, M., Lu, C.: Intrinsic images by entropy minimization. In: Proc. ECCV, pp. 582–595 (2004)

  10. Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press (2004)

  11. Hasenfratz, J., Lapierre, M., Holzschuch, N., Sillion, F.: A survey of real-time soft shadows algorithms. Computer Graphics Forum 22(4), 753–774 (2003)

    Google Scholar 

  12. Kersten, D., Mamassian, P., Knill, D.C.: Moving cast shadows induce apparent motion in depth. Perception 26(2), 171–192 (1997)

    Google Scholar 

  13. Li, Y., Lin, S., Lu, H., Shum, H.: Multiple-cue illumination estimation in textured scenes. In: Proc. IEEE ICCV, pp. 1366–1373 (2003)

  14. Li, Y., Sun, J., Tang, C.K., Shum, H.Y.: Lazy snapping. ACM Trans. Graph. 23(3), 303–308 (2004)

    Google Scholar 

  15. Liebowitz, D., Zisserman, A.: Combining scene and auto-calibration constraints. In: Proc. IEEE ICCV, pp. 293–300 (1999)

  16. Nadimi, S., Bhanu, B.: Physical models for moving shadow and object detection in video. IEEE Trans. Pattern Anal. Mach. Intell. 26(8), 1079–1087 (2004)

    Google Scholar 

  17. Petrovic, L., Fujito, B., Williams, L., Finkelstein, A.: Shadows for cel animation. In: Proc. ACM SIGGRAPH, pp. 511–516 (2000)

  18. Rother, C., Kolmogorov, V., Blake, A.: grabcut : interactive fore-ground extraction using iterated graph cuts. ACM Trans. Graph. 23(3), 309–314 (2004)

    Google Scholar 

  19. Sato, I., Sato, Y., Ikeuchi, K.: Stability issues in recovering illumination distribution from brightness in shadows. In: Proc. IEEE CVPR, pp. 400–407 (2001)

  20. Smith, A.R., Blinn, J.F.: Blue screen matting. In: Proc. ACMSIG-GRAPH, pp. 259–268 (1996)

  21. Springer, C.E.: Geometry and Analysis of Projective Spaces. Free-man (1964) 23. Tappen, M.F., Freeman, W.T., Adelson, E.H.: Recovering intrinsic images from a single image. In: Advances in Neural Information Processing Systems (2002)

  22. Sun, J., Jia, J., Tang, C., Shum, H.: Poisson matting. ACM Trans. Graph. 23(3), 315–321 (2004)

    Google Scholar 

  23. Tappen, M.F., Freeman, W.T., Adelson, E.H.: Recovering intrinsic images from a single image. In: Advances in Neural Information Processing Systems (2002)

  24. Weiss, Y.: Deriving intrinsic images from image sequences. In: Proc. IEEE ICCV, pp. 68–75 (2001)

  25. Wright, S.: Digital Compositing for Film and Video. Focal Press (2001)

Download references

Author information

Authors and Affiliations

  1. School of Computer Science, University of Central Florida, Orlando, FL, 32816, USA

    Xiaochun Cao, Yuping Shen, Mubarak Shah & Hassan Foroosh

Authors
  1. Xiaochun Cao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuping Shen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mubarak Shah
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Hassan Foroosh
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiaochun Cao.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Cao, X., Shen, Y., Shah, M. et al. Single view compositing with shadows. Visual Comput 21, 639–648 (2005). https://doi.org/10.1007/s00371-005-0335-x

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00371-005-0335-x

Keywords

Search

Navigation