Advertisement

Gradient Based Image Completion by Solving Poisson Equation

  • Jianbing Shen
  • Xiaogang Jin
  • Chuan Zhou
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3767)

Abstract

Image completion is a method to fill the missing portions of an image caused by the removal of one or more foreground or background elements. In this paper a novel image completion algorithm is proposed for removing significant objects from natural images or photographs. The completion is realized in the following three steps. First, a gradient-based model is presented to determine the gradient-patch filling order. This step is critical because a better filling order can improve the continuation of image structures. Second, we implement the gradient-patch update strategy by measuring the exponential distance between the source patch and the target one in gradient domain. In order to find a better patch matching and propagating algorithm, we incorporate the gradient and color information together to determine the target patch. Third, a complete image is achieved by solving the Poisson equation with the updated image gradient map. Some experimental results on real-scene photographs are given to demonstrate both the efficiency and image equality of our novel method.

Keywords

Peak Signal Noise Ratio Unknown Region Image Completion Source Patch Target Patch 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Agarwala, A., Dontcheva, M., Agarwala, M., Drucker, S., Colburn, A., Curless, B., Salesin, D., Cohen, M.: Interactive digital photomontage. In: Proceedings of ACM SIGGRAPH, pp. 294–302. ACM Press, New York (2004)Google Scholar
  2. 2.
    Levin, A., Zomet, A., Weiss, Y.: Learning how to inpaint from global image statistics. In: ICCV, pp. 305–361 (2003)Google Scholar
  3. 3.
    Bornard, R., Lecan, E., Laborelli, L., Chenot, J.H.: Missing data correction in still images and image sequences. In: ACM Multimedia, France, pp. 355–361 (2002)Google Scholar
  4. 4.
    Bertalmio, M., Sapiro, G., Caselles, V., Ballester, C.: Image inpainting. In: Proceedings of ACM SIGGRAPH, pp. 417–424. ACM Press, New York (2000)Google Scholar
  5. 5.
    Criminisi, A., Perez, P., Toyama, K.: Object removal by exemplar-based inpainting. IEEE Transactions on Image Processing, 1200–1212 (2004)Google Scholar
  6. 6.
    Drori, I., Cohen-Or, D., Yeshurun, H.: Fragment-based image completion. In: Proceedings of ACM SIGGRAPH, pp. 303–312. ACM Press, New York (2003)Google Scholar
  7. 7.
    Fatal, R., Lischinski, D., Werman, M.: Gradient domain high dynamic range compression. In: Proceedings of ACM SIGGRAPH, pp. 249–256 (2002)Google Scholar
  8. 8.
    Harrison, P.: A non-hierarchical procedure for re-synthesis of complex texture. In: WSCG, pp. 190–197. Czech Republic (2001)Google Scholar
  9. 9.
    Jia, J., Tang, C.K.: Image repairing: Robust image synthesis by adaptive tensor voting. In: CVPR, Madison, WI, pp. 643–650 (2003)Google Scholar
  10. 10.
    Press, W., Teukolsky, S., Vetterling, W., Flannery, B.: Numerical Recipes in C: The Art of Scientific Computing. Cambridge University Press, Cambridge (1992)Google Scholar
  11. 11.
    Perez, P., Gangnet, M., Blake, A.: Poisson image editing. In: Proceedings of ACM SIGGRAPH, pp. 313–318. ACM Press, New York (2003)Google Scholar
  12. 12.
    Raskar, R., Tan, K., Feris, R., Yu, J., Turk, M.: Non-photorealistic camera: depth edge detection and stylized rendering using multi-flash imaging. In: Proceedings of ACM SIGGRAPH, pp. 679–688. ACM Press, New York (2004)Google Scholar
  13. 13.
    Raskar, R., Ilie, A., Yu, J.: Image fusion for context enhancement and video surrealism. In: NPAR, pp. 85–95 (2004)Google Scholar
  14. 14.
    Sun, J., Jia, J., Tang, C.K., Shum, H.Y.: Poisson matting. In: Proceedings of ACM SIGGRAPH, pp. 315–321. ACM Press, New York (2004)Google Scholar
  15. 15.
    Wexler, Y., Shechtman, E., Irani, M.: Space-Time Video Completion. In: CVPR, Washington, D.C., USA, pp. 120–127 (2004)Google Scholar
  16. 16.
    Zhang, Y.J., Xiao, J.J., Shah, M.: Region Completion in a Single Image. In: EUROGRAPHICS, Grenoble, France, Short Presentations (2004)Google Scholar
  17. 17.
    Zhang, Y.J., Xiao, J.J., Shah, M.: Motion Layer Based Object Removal in Videos. In: WACV, pp. 516–521 (2005)Google Scholar
  18. 18.
    Agrawal, A., Raskar, R., Nayar, S., Li, Y.: Removing Flash Artifacts using Gradient Analysis. In: Proceedings of ACM SIGGRAPH. ACM Press, New York (2005) (to appear)Google Scholar
  19. 19.
    Sun, J., Yuan, L., Jia, J., Shum, H.Y.: Image Completion with Structure Propagation. In: Proceedings of ACM SIGGRAPH. ACM Press, New York (2005) (to appear)Google Scholar
  20. 20.
    Sharf, A., Alexa, M., Cohen-Or, D.: Context-based surface completion. In: Proceedings of ACM SIGGRAPH, pp. 878–887. ACM Press, New York (2004)Google Scholar
  21. 21.
    Kasson, J.M., Plouffe, W.: An analysis of selected computer interchange color spaces. In: Proceedings of ACM SIGGRAPH, pp. 373–405. ACM Press, New York (1992)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Jianbing Shen
    • 1
  • Xiaogang Jin
    • 1
  • Chuan Zhou
    • 1
  1. 1.State Key Lab of CAD&CGZhejiang UniversityHangzhouP.R. China

Personalised recommendations