Advertisement

Real-time feature-based image morphing for memory-efficient impostor rendering and animation on GPU

Abstract

Real-time rendering of large animated crowds consisting of thousands of virtual humans is important for several applications including simulations, games, and interactive walkthroughs but cannot be performed using complex polygonal models at interactive frame rates. For that reason, methods using large numbers of precomputed image-based representations, called impostors, have been proposed. These methods take advantage of existing programmable graphics hardware to compensate for computational expense while maintaining visual fidelity. Thanks to these methods, the number of different virtual humans rendered in real time is no longer restricted by computational power but by texture memory consumed for the variety and discretization of their animations. This work proposes a resource-efficient impostor rendering methodology that employs image morphing techniques to reduce memory consumption while preserving perceptual quality, thus allowing higher diversity or resolution of the rendered crowds. Results of the experiments indicated that the proposed method, in comparison with conventional impostor rendering techniques, can obtain 38 % smoother animations or 87 % better appearance quality by reducing the number of key-frames required for preserving the animation quality via resynthesizing them with up to 92 % similarity on real time.

This is a preview of subscription content, log in to check access.

Access options

Buy single article

Instant unlimited access to the full article PDF.

US$ 39.95

Price includes VAT for USA

Subscribe to journal

Immediate online access to all issues from 2019. Subscription will auto renew annually.

US$ 199

This is the net price. Taxes to be calculated in checkout.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15

References

  1. 1.

    Schaufler, G., Stürzlinger, W.: A three dimensional image cache for virtual reality. Comput. Graph. Forum 15(3), 227–235 (1996)

  2. 2.

    Shade, J., Lischinski, D., Salesin, D.H., DeRose, T., Snyder, J.: Hierarchical image caching for accelerated walkthroughs of complex environments. In: Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques, New York, NY, USA, pp. 75–82 (1996)

  3. 3.

    Millan, E., Rudomin, I.: Impostors and pseudo-instancing for GPU crowd rendering. In: Proceedings of the 4th International Conference on Computer Graphics and Interactive Techniques in Australasia and Southeast Asia, pp. 49–55, New York, NY, USA (2006)

  4. 4.

    Reynolds, C.: Big fast crowds on PS3. In: Proceedings of the 2006 ACM SIGGRAPH symposium on Videogames, New York, NY, USA, pp. 113–121 (2006)

  5. 5.

    Treuille, A., Cooper, S., Popović, Z.: Continuum crowds. In: ACM SIGGRAPH 2006 Papers, New York, NY, USA, pp. 1160–1168 (2006)

  6. 6.

    Thalmann, D., Grillon, H., Maim, J., Yersin, B.: Challenges in crowd simulation. In: International Conference on CyberWorlds, CW ’09, pp. 1–12 (2009)

  7. 7.

    Seitz, S.M., Dyer, C.R.: View morphing. In: Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques, pp. 21–30 (1996)

  8. 8.

    Beier, T., Neely, S.: Feature-based image metamorphosis. SIGGRAPH Comput. Graph. 26(2), 35–42 (1992)

  9. 9.

    Aubel, A., Boulic, R., Thalmann, D.: Real-time display of virtual humans: levels of details and impostors. IEEE Trans. Circuits Syst. Video Technol. 10(2), 207–217 (2000)

  10. 10.

    Hamill, J., McDonnell, R., Dobbyn, S., O’Sullivan, C.: Perceptual evaluation of impostor representations for virtual humans and buildings. Comput. Graph. Forum 24(3), 623–633 (2005)

  11. 11.

    Yuksel, K.A., Yucebilgin, A., Balcisoy, S., Ercil, A.: Using image morphing for memory-efficient impostor rendering on GPU. In: International Conference on CyberWorlds, CW, pp. 197–202 (2001)

  12. 12.

    Tecchia, F., Chrysanthou, Y.: Real-time rendering of densely populated urban environments. In: Proceedings of the Eurographics Workshop on Rendering Techniques 2000, London, UK, pp. 83–88 (2000)

  13. 13.

    Tecchia, F., Loscos, C., Chrysanthou, Y.: Visualizing crowds in real-time. Comput. Graph. Forum 21(4), 753–765 (2002)

  14. 14.

    Dobbyn, S., Hamill, J., O’Conor, K., O’Sullivan, C.: Geopostors: a real-time geometry/impostor crowd rendering system. In: Proceedings of the 2005 Symposium on Interactive 3D Graphics and Games, New York, NY, USA, pp. 95–102 (2005)

  15. 15.

    Kavan, L., Dobbyn, S., Collins, S., Žára, J., O’Sullivan, C.: Polypostors: 2D polygonal impostors for 3D crowds. In: Proceedings of the 2008 Symposium on Interactive 3D Graphics and Games, New York, NY, USA, pp. 149–155 (2008)

  16. 16.

    Lister, W., Laycock, R.G., Day, A.M.: A dynamic cache for real-time crowd rendering. Comput. Graph. Forum (2010)

  17. 17.

    Stich, T., Linz, C., Wallraven, C., Cunningham, D., Magnor, M.: Perception-motivated interpolation of image sequences. ACM Trans. Appl. Percept. 8(2), 11 (2011)

  18. 18.

    Zamith, M., et al.: Real time feature-based parallel morphing in GPU applied to texture-based animation. In: 16th International Conference on Systems, Signals and Image Processing, IWSSIP 2009, pp. 1–4 (2009)

  19. 19.

    Wong, T.Y., Kovesi, P., Datta, A.: Towards quantitative measures of image morphing quality. In: Digital Image Computing: Techniques and Applications, DICTA’05, Proceedings, pp. 19–20 (2005)

  20. 20.

    Gao, P., Sederberg, T.W.: A work minimization approach to image morphing. Vis. Comput. 14(8–9), 390–400 (1998)

  21. 21.

    Karungaru, S., Fukumi, M., Akamatsu, N.: Automatic human faces morphing using genetic algorithms based control points selection. Int. J. Innov. Comput. Inf. Control 3, 247–256 (2007)

  22. 22.

    Lowe, D.G.: Object recognition from local scale-invariant features. In: The Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 2, pp. 1150–1157 (1999)

Download references

Acknowledgements

The authors would like to thank anonymous reviewers at CW2011 and TVCJ for their comments that helped us to improve the quality of this manuscript.

Author information

Correspondence to Kamer Ali Yuksel.

Additional information

This work has been partially supported by TUBITAK under project 109E134, VIPSAFE.

Electronic Supplementary Material

Below is the link to the electronic supplementary material.

(MOV 66.8 MB)

(MOV 66.8 MB)

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Yuksel, K.A., Yucebilgin, A., Balcisoy, S. et al. Real-time feature-based image morphing for memory-efficient impostor rendering and animation on GPU. Vis Comput 29, 131–140 (2013). https://doi.org/10.1007/s00371-012-0718-8

Download citation

Keywords

  • Crowd simulation
  • Impostor rendering
  • Image and view morphing
  • Graphical processing unit