Fast Shape-Simplifying Image Abstraction Using Graphics Hardware

  • Hanli Zhao
  • Xiaogang Jin
  • Jianbing Shen
  • Li Shen
  • Ruifang Pan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5670)


This paper presents a new GPU-based method for creating abstracted representations of photographs. Based on the constrained mean curvature flow and the Shock filter, our approach simplifies both shapes and colors simultaneously while preserving and conveying the directionality of important features and shape boundaries. The level of abstraction can be intuitively controlled by iteratively and incrementally applying the algorithm. Note that the whole pipeline design is highly parallel, enabling a GPU-based implementation. Our GPU-based method outperforms the CPU-based one with two magnitudes of speedup. Several experimental examples are shown to demonstrate both the effectiveness and efficiency of the proposed method.


Non-photorealistic rendering image abstraction flow-based filtering GPU 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Blythe, D.: The Direct 3D 10 system. In: Proc. ACM SIGGRAPH 2006, pp. 724–734. ACM, New York (2006)CrossRefGoogle Scholar
  2. 2.
    Cabral, B., Leedom, L.C.: Imaging vector fields using line integral convolution. In: Proc. ACM SIGGRAPH 1993, pp. 263–270 (1993)Google Scholar
  3. 3.
    Catté, F., Lions, P., Morel, J., Coll, T.: Image selective smoothing and edge detection by nonlinear diffusion. SIAM Journal on Numerical Analysis 29(1), 182–193 (1992)MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    Chen, J., Paris, S., Durand, F.: Real-time edge-aware image processing with the bilateral grid. ACM Trans. Graphics (SIGGRAPH 2007) 26(3), article 103 (2007) Google Scholar
  5. 5.
    Collomosse, J.P., Rowntree, D., Hall, P.M.: Stroke surfaces: temporally coherent artistic animations from video. IEEE Trans. Visualization and Computer Graphics 11(5), 540–549 (2005)CrossRefGoogle Scholar
  6. 6.
    DeCarlo, D., Santella, A.: Stylization and abstraction of photographs. ACM Trans. Graphics (SIGGRAPH 2002) 21(3), 769–776 (2002)Google Scholar
  7. 7.
    Farbman, Z., Fattal, R., Lischinski, D., Szeliski, R.: Edge-preserving decompositions for multi-scale tone and detail manipulation. ACM Trans. Graphics (SIGGRAPH 2008) 27(3), article 67 (2008)Google Scholar
  8. 8.
    Kang, H., Lee, S., Chui, C.K.: Coherent line drawing. In: Proc. ACM Sym. Non-Photorealistic Animation and Rendering (NPAR 2007), pp. 43–50 (2007)Google Scholar
  9. 9.
    Kang, H., Lee, S.: Shape-simplifying image abstraction. Computer Graphics Forum (PG 2008) 27(7), 61–68 (2008)MathSciNetGoogle Scholar
  10. 10.
    McCloud, S.: UnderStanding comics. Harper Collins Publishers, New York (1993)Google Scholar
  11. 11.
    Orzan, A., Bousseau, A., Barla, P., Thollot, J.: Structure-preserving manipulation of photographs. In: Proc. ACM Sym. Non-Photorealistic Animation and Rendering (NPAR 2007), pp. 103–110 (2007)Google Scholar
  12. 12.
    Osher, S., Rudin, L.I.: Feature-oriented image enhancement using shock filters. SIAM Journal on Numerical Analysis 27(4), 919–940 (1990)CrossRefzbMATHGoogle Scholar
  13. 13.
    Wang, J., Xu, Y., Shum, H.Y., Cohen, M.F.: Video tooning. ACM Trans. Graphics (SIGGRAPH 2004) 23(3), 574–583 (2004)CrossRefGoogle Scholar
  14. 14.
    Wen, F., Luan, Q., Liang, L., Xu, Y.Q., Shum, H.Y.: Color sketch generation. In: Proc. ACM Sym. Non-Photorealistic Animation and Rendering (NPAR 2006), pp. 47–54 (2006)Google Scholar
  15. 15.
    Winnemöller, H., Olsen, S.C., Gooch, B.: Real-time video abstraction. ACM Trans. Graphics (SIGGRAPH 2006) 25(3), 1221–1226 (2006)CrossRefGoogle Scholar
  16. 16.
    Zhao, H., Jin, X., Shen, J., Mao, X., Feng, J.: Real-time feature-aware video abstraction. The Visual Computer (CGI 2008) 24(7-9), 727–734 (2008)CrossRefGoogle Scholar
  17. 17.
    Zhao, H., Mao, X., Jin, X., Shen, J., Wei, F.: Real-time saliency-aware video abstraction. The Visual Computer (in press, 2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Hanli Zhao
    • 1
  • Xiaogang Jin
    • 1
  • Jianbing Shen
    • 2
  • Li Shen
    • 1
  • Ruifang Pan
    • 3
  1. 1.State Key Lab of CAD & CGZhejiang UniversityChina
  2. 2.School of Computer & TechnologyBeijing Institute of TechnologyChina
  3. 3.Zhejiang University of Media and CommunicationsChina

Personalised recommendations