The Visual Computer

, Volume 31, Issue 6–8, pp 893–904 | Cite as

Efficient multi-constrained optimization for example-based synthesis

  • Stefan Hartmann
  • Elena Trunz
  • Björn Krüger
  • Reinhard Klein
  • Matthias B. Hullin
Original Article

Abstract

Digital media content comes in a wide variety of modalities and representations. Although they have obvious semantic and structural difference, many of them can be unwrapped into a one-dimensional parameter domain, e.g., time, one spatial dimension. Novel content can then be generated in this parameter domain by computing sequences of elements that are optimal according to an objective to be minimized and in addition satisfy a number of user-defined constraints. Examples for this type of content generation task are audio synthesis, human motion synthesis or architectural texture synthesis. In that work, we present a generalized algorithm for this type of content generation task. We demonstrate the potential of our technique on a selection of content creation tasks, namely the generation of extended animation sequences from motion capture libraries and the example-based synthesis of architectural geometry such as buildings and street blocks.

Keywords

Example-based synthesis Data-driven animation Motion synthesis Building layouts 

Supplementary material

371_2015_1114_MOESM1_ESM.pdf (200 kb)
Supplementary material 1 (pdf 200 KB)

References

  1. 1.
    Bokeloh, M., Wand, M., Seidel, H.-P.: A connection between partial symmetry and inverse procedural modeling. In: ACM SIGGRAPH 2010 Papers, SIGGRAPH ’10, Los Angeles, California, pp. 104:1–104:10 (2010)Google Scholar
  2. 2.
    Eppstein, D.: Finding the \(k\) shortest paths. In: Proceedings of the 35th symposium on Foundations of Computer Science, pp. 154–165. IEEE, November 1994Google Scholar
  3. 3.
    Garcia, R.: Resource constrained shortest paths and extensions. PhD thesis, Georgia Institute of Technology (2009)Google Scholar
  4. 4.
    Horswill, I.D., Foged, L.: Fast procedural level population with playability constraints. In AIIDE (2012)Google Scholar
  5. 5.
    Kovar, L., Gleicher, M., Pighin, F.: Motion graphs. ACM Trans. Graph. (Proc. SIGGRAPH) 21(3), 473–482 (2002)CrossRefGoogle Scholar
  6. 6.
    Kovar, L., Gleicher, M., Schreiner, J.: Footskate cleanup for motion capture editing. In ACM SIGGRAPH symposium on computer animation, pp. 97–104 (2002)Google Scholar
  7. 7.
    Krüger, B., Tautges, J., Weber, A., Zinke, A.: Fast local and global similarity searches in large motion capture databases. In ACM SIGGRAPH symposium on computer animation, pp. 1–10, July 2010Google Scholar
  8. 8.
    Lan, R., Sun, H.: Automated human motion segmentation via motion regularities. Vis. Comput. 31(1), 35–53 (2015)CrossRefGoogle Scholar
  9. 9.
    Lee, J., Chai, J., Reitsma, P.S.A., Hodgins, J.K., Pollard, N.S.: Interactive control of avatars animated with human motion data. ACM Trans. Graph. (Proc. SIGGRAPH) 31(5), 491–500 (2002)Google Scholar
  10. 10.
    Lefebvre, S., Hornus, S., Lasram, A.: By-example synthesis of architectural textures. In: ACM SIGGRAPH 2010 Papers, SIGGRAPH ’10, Los Angeles, California, pp. 84:1–84:8 (2010)Google Scholar
  11. 11.
    Lo, W.-Y., Zwicker, M.: Bidirectional search for interactive motion synthesis. Comput. Graph. Forum 29(2), 563–573 (2010)CrossRefGoogle Scholar
  12. 12.
    Merrell, P., Manocha, D.: Constraint-based model synthesis. In SIAM/ACM conference on geometric and physical modeling, pp. 101–111, (2009)Google Scholar
  13. 13.
    Min, J., Chai, J.: Motion graphs++: a compact generative model for semantic motion analysis and synthesis. ACM Trans. Graph. 31(6), 153:1–153:12 (2012)CrossRefGoogle Scholar
  14. 14.
    Müller, M., Röder, T., Clausen, M., Eberhardt, B., Krüger, B., Weber, A.: Documentation Mocap Database HDM05. Technical Report CG-2007-2, Universität Bonn, June 2007Google Scholar
  15. 15.
    Müller, P., Wonka, P., Haegler, S., Ulmer, A., Van Gool, L.: Procedural modeling of buildings. ACM Trans. Graph. (Proc. SIGGRAPH) 25(3), 614–623 (2006)CrossRefGoogle Scholar
  16. 16.
    Ribeiro, C.C., Minoux, M.: A heuristic approach to hard constrained shortest path problems. Discret. Appl. Math. 10(2), 125–137 (1985)MATHMathSciNetCrossRefGoogle Scholar
  17. 17.
    Safonova, A., Hodgins, J.K.: Construction and optimal search of interpolated motion graphs. In: ACM SIGGRAPH 2007 Papers, SIGGRAPH ’07, Los Angeles, California (2007)Google Scholar
  18. 18.
    Smith, G., Treanor, M., Whitehead, J., Mateas, M.: Rhythm-based level generation for 2d platformers. In: Conference on Foundations of Digital Games, pp. 175–182 (2009)Google Scholar
  19. 19.
    Talton, J.O., Lou, Y., Lesser, S., Duke, J., Měch, R., Koltun, V.: Metropolis procedural modeling. ACM Trans. Graph. 30(2), 11:1–11:14 (2011)CrossRefGoogle Scholar
  20. 20.
    Turner, L.: Variants of shortest path problems. Algorithm. Oper. Res. 6(2), 91–104 (2011)MATHGoogle Scholar
  21. 21.
    Vögele, A., Krüger, B., Klein, R.: Efficient unsupervised temporal segmentation of human motion. In ACM SCA, July 2014Google Scholar
  22. 22.
    Wenner, S., Bazin, J.-C., Sorkine-Hornung, A., Kim, C., Gross, M.: Scalable music: automatic music retargeting and synthesis. Proc. Eurograph. 32(2), 345–354 (2013)Google Scholar
  23. 23.
    Yeh, Y., Breeden, K., Yang, L., Fisher, M., Hanrahan, P.: Synthesis of tiled patterns using factor graphs. ACM Trans. Graph. 32(1), 614–623 (2012)Google Scholar
  24. 24.
    Zhou, F., De la Torre, F., Hodgins, J.: Aligned cluster analysis for temporal segmentation of human motion. In: IEEE conference on Automatic Face and Gestures Recognition (2008)Google Scholar
  25. 25.
    Zhou, S., Jiang, C., Lefebvre, S.: Topology-constrained synthesis of vector patterns. ACM Trans. Graph. 33(6), 215:1–215:11 (2014)Google Scholar
  26. 26.
    Zhou, S., Lasram, A., Lefebvre, S.: By-example synthesis of curvilinear structured patterns. Comput. Graph. Forum 32(2), 355–360 (2013)Google Scholar
  27. 27.
    Zhu, X., Wilhelm, W.E.: A three-stage approach for the resource-constrained shortest path as a sub-problem in column generation. Comput. Oper. Res. 39(2), 164–178 (2012)MATHMathSciNetCrossRefGoogle Scholar
  28. 28.
    Ziegelmann, M.: Constrained shortest paths and related problems. PhD thesis, Saarland University (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Stefan Hartmann
    • 1
  • Elena Trunz
    • 1
  • Björn Krüger
    • 1
  • Reinhard Klein
    • 1
  • Matthias B. Hullin
    • 1
  1. 1.Institute of Computer Science IIUniversity of BonnBonnGermany

Personalised recommendations