Natural Image Composition with Inhomogeneous Boundaries

  • Dong Wang
  • Weijia Jia
  • Guiqing Li
  • Yunhui Xiong
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7088)


Image composition usually floods the composition region of a target image with the same shape as a source image patch. To achieve seamless transition effect, the tone of the boundary in the target image is then transferred to the interior region of the source patch. Traditional approaches usually fail to work for the case that the corresponding boundaries of target and source images don’t match well because the tone transformation of all pixels on the boundary are equally propagated to the inner region. This paper presents a new image composition technique based on discrete mean value coordinates(DMVC), which supports the transition of tone transformation of part selected not all pixels on the boundary to the inner region. The approach works as follows. It firstly selects boundary pixels having good matching. The new color of inner pixels is then calculated using DMVC according to those selected pixel pairs from the source and target boundaries. Matting technique is finally introduced to compose the new pixels to the target image. Experiments show that the proposed approach can obtain reasonable results for examples with inconsistent boundaries between source and target images.


Image composition Discrete mean value coordinates Image editing Edit propagation 


  1. 1.
    Yang, W., Zheng, J., Cai, J., Rahardja, S., Chen, C.: Natural and seamless image composition with color control. IEEE Transactions on Image Processing 18(11), 2584–2592 (2009)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Jia, J., Sun, J., Tang, C.-K., Shum, H.-Y.: Drag-and-drop pasting. ACM Siggraph 25(3), 631–636 (2006)CrossRefGoogle Scholar
  3. 3.
    Pérez, P., Gangnet, M., Blake, A.: Poisson image editing. ACM Siggraph 22(3), 313–318 (2003)CrossRefGoogle Scholar
  4. 4.
    Farbman, Z., Hoffer, G., Lipman, Y., Cohen-Or, D., Fattal, R., Lischinski, D.: Coordinates for instant image cloning. ACM Trans. on Graphics 28(3), 67:1–67:10 (2009)CrossRefGoogle Scholar
  5. 5.
    Chen, T., Cheng, M.-M., Tan, P., Shamir, A., Hu, S.-M.: Sketch2photo:Internet image montage. ACM Trans. Graph. 28(5) (2009)Google Scholar
  6. 6.
    Ding, M., Tong, R.: Content-aware copying and pasting in images. The Visual Computer 26, 721–729 (2010)CrossRefGoogle Scholar
  7. 7.
    Sun, J., Jia, J., Tang, C.-K., Shum, H.-Y.: Poisson matting. Proceedings of ACM SIGGRAPH 23(3), 315–321 (2004)CrossRefGoogle Scholar
  8. 8.
    Levin, A., Lischinski, D., Weiss, Y.: A closed form solution to natural image matting. In: Proceedings of IEEE CVPR (2006)Google Scholar
  9. 9.
    Rother, C., Kolmogorov, V., Blake, A.: Grabcut - interactive foreground extraction using iterated graph cut. Proceedings of ACM SIGGRAPH 23(3), 309–314 (2004)CrossRefGoogle Scholar
  10. 10.
    Agarwala, A.: Efficient gradient-domain compositing using quadtrees. ACM Trans. Graph. 26(3), 94:1–94:6 (2007)CrossRefGoogle Scholar
  11. 11.
    Kazhdan, M., Hoppe, H.: Streaming multigrid for gradient-domain operations on large images. ACM Trans. Graph. 27(3), 21:1–21:10 (2008)CrossRefGoogle Scholar
  12. 12.
    Bolz, J., Farmer, I., Grinspun, E., Schroder, P.: Sparse matrix solvers on the GPU: conjugate gradients and multigrid. ACM Trans. Graph. 22(3), 917–924 (2003)CrossRefGoogle Scholar
  13. 13.
    Tao, M.W., Johnson, M.K., Paris, S.: Error-Tolerant Image Compositing. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 31–44. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  14. 14.
    Floater, M.S.: Mean value coordinates. CAGD 20(1), 19–27 (2003)MathSciNetzbMATHGoogle Scholar
  15. 15.
    Hormann, K., Floater, M.S.: Mean value coordinates for arbitrary planar polygons. ACM Transactions on Graphics 25(4), 1424–1441 (2006)CrossRefGoogle Scholar
  16. 16.
    Lipman, Y., Kopf, J., Cohen-Or, D., Levin, D.: GPU-assisted positive mean value coordinates for mesh deformations. In: SGP 2007, pp. 117–123 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Dong Wang
    • 1
  • Weijia Jia
    • 1
  • Guiqing Li
    • 2
  • Yunhui Xiong
    • 2
  1. 1.City University of Hong KongChina
  2. 2.South China University of TechnologyChina

Personalised recommendations