Painterly rendering controlled by multiscale image features

ABSTRACT

What we present in this paper is a 2D non-photorealistic, stroke-based image rendering technique, which is a fully automatic template-based painting method controlled by the structure of the model image. Namely it is based on dominant, weighted image edges and ridges extracted by a multiscale edge/ridge detection method. Stroke sizes (scales) and painting directions are both controlled by edge and ridge weights and orientations. This way the painting process becomes more "natural" in the sense that all of its parameters are guided by image features. We also present different painting variations based on this technique.

REFERENCES

• 1: J Canny, A computational approach to edge detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.8 n.6, p.679-698, Nov. 1986 [doi>10.1109/TPAMI.1986.4767851]
• 2: Paul Haeberli, Paint by numbers: abstract image representations, Proceedings of the 17th annual conference on Computer graphics and interactive techniques, p.207-214, September 1990, Dallas, TX, USA
• 3: Aaron Hertzmann, Painterly rendering with curved brush strokes of multiple sizes, Proceedings of the 25th annual conference on Computer graphics and interactive techniques, p.453-460, July 1998 [doi>10.1145/280814.280951]
• 4: Robert D. Kalnins , Lee Markosian , Barbara J. Meier , Michael A. Kowalski , Joseph C. Lee , Philip L. Davidson , Matthew Webb , John F. Hughes , Adam Finkelstein, WYSIWYG NPR: drawing strokes directly on 3D models, ACM Transactions on Graphics (TOG), v.21 n.3, July 2002
• 5: Kato, Z., Sziranyi, T., Ji, X., Toth, Z., and Czuni, L. 2002. Content-based image retrieval using stochastic paintbrush transformation. In Proceedings of ICIP.
• 6: Kovacs, L., and Sziryanyi, T. 2002. Creating animations combining stochastic paintbrush transformation and motion detection. In Proceedings of 16th ICPR, IAPR&IEEE, vol. 2, 1090--1093.
• 7: Kovacs, L., and Sziranyi, T. 2004. Coding of stroke-based animations. In WSCG 2004 Posters Papers Proceedings, 81--84.
• 8: Levente Kovacs , Tamas Sziranyi, Efficient Coding of Stroke-Rendered Paintings, Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2, p.835-838, August 23-26, 2004 [doi>10.1109/ICPR.2004.323]
• 9: Tony Lindeberg, Feature Detection with Automatic Scale Selection, International Journal of Computer Vision, v.30 n.2, p.79-116, Nov. 1998 [doi>10.1023/A:1008045108935]
• 10: Peter Litwinowicz, Processing images and video for an impressionist effect, Proceedings of the 24th annual conference on Computer graphics and interactive techniques, p.407-414, August 1997 [doi>10.1145/258734.258893]
• 11: Barbara J. Meier, Painterly rendering for animation, Proceedings of the 23rd annual conference on Computer graphics and interactive techniques, p.477-484, August 1996 [doi>10.1145/237170.237288]
• 12: J. D. Northrup , Lee Markosian, Artistic silhouettes: a hybrid approach, Proceedings of the 1st international symposium on Non-photorealistic animation and rendering, p.31-37, June 05-07, 2000, Annecy, France [doi>10.1145/340916.340920]
• 13: Anthony Santella , Doug DeCarlo, Abstracted painterly renderings using eye-tracking data, Proceedings of the 2nd international symposium on Non-photorealistic animation and rendering, June 03-05, 2002, Annecy, France [doi>10.1145/508530.508544]
• 14: Sziranyi, T., and Toth, Z. 2000. Random paintbrush transformation. In Proceedings of 15th ICPR, IAPR&IEEE, 155--158.
• 15: Tamás Szirányi , Zoltán Tóth, Optimization of Paintbrush Rendering of Images by Dynamic MCMC Methods, Proceedings of the Third International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition, p.201-215, September 03-05, 2001

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.3 COMPUTER GRAPHICS
      I.3.3 Picture/Image Generation

Additional Classification:
  I. Computing Methodologies
  I.3 COMPUTER GRAPHICS
      I.3.3 Picture/Image Generation
          Subjects: Display algorithms; Line and curve generation

Keywords:
automatic painting, image decomposition, stochastic painting, stroke based rendering