Watertight Multi-view Reconstruction Based on Volumetric Graph-Cuts

  • Mario Sormann
  • Christopher Zach
  • Joachim Bauer
  • Konrad Karner
  • Horst Bishof
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4522)

Abstract

This paper proposes a fast 3D reconstruction approach for efficiently generating watertight 3D models from multiple short baseline views. Our method is based on the combination of a GPU-based plane-sweep approach, to compute individual dense depth maps and a subsequent robust volumetric depth map integration technique. Basically, the dense depth map values are transformed to a volumetric grid, which are further embedded in a graph structure. The edge weights of the graph are derived from the dense depth map values and if available, from sparse 3D information. The final optimized surface is obtained as a min-cut/max-flow solution of the weighted graph. We demonstrate the robustness and accuracy of our proposed approach on several real world data sets.

Keywords

volumetric 3D reconstruction graph-cut dense depth maps virtual 3D models 

References

  1. 1.
    Bauer, J., Zach, C., Karner, K., Bischof, H.: Efficient sparse 3d reconstruction by space sweeping. In: 3DPVT, Chapel Hill, USA, CD Proceedings (June 2006)Google Scholar
  2. 2.
    Collins, R.T.: A space-sweep approach to true multi-image matching. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, USA, June 1996, pp. 358–363 (1996)Google Scholar
  3. 3.
    Curless, B., Levoy, M.: A volumetric method for building complex models from range images. In: ACM SIGGRAPH, vol. 1, New Orleans, USA, August 1996, pp. 303–312. ACM Press, New York (1996)Google Scholar
  4. 4.
    Debevec, P.E., Taylor, J., Malik, J.: Modeling and rendering architecture from photographs. In: ACM SIGGRAPH, New Orleans, USA, August 1996, pp. 11–20. ACM Press, New York (1996)Google Scholar
  5. 5.
    El-Hakim, S.F., Beraldin, J.A.: Configuration analysis for sensor integration. In: Proceedings of SPIE, vol. 2, Philadelphia, USA, October 1995, pp. 274–285 (1995)Google Scholar
  6. 6.
    Furukawa, Y., Ponce, J.: High-fidelity image-based modeling. Tech. rep., UIUC (2006)Google Scholar
  7. 7.
    Goesele, M., Curless, B., Seitz, S.: Multi-view stereo revisited. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, New York, USA, June 2006, pp. 2402–2409 (2006)Google Scholar
  8. 8.
    Heikkilä, J.: Geometric camera calibration using cicular control points. IEEE Transactions on Pattern Analysis and Machine Intelligence 22(10), 1066–1077 (2000)CrossRefGoogle Scholar
  9. 9.
    Hornung, A., Kobbelt, L.: Hierarchical volumetric multi-view stereo reconstruction of manifold surfaces based on dual graph embedding. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, New York, USA, June 2006, pp. 503–510 (2006)Google Scholar
  10. 10.
    Hornung, A., Kobbelt, L.: Robust reconstruction of watertight 3d models from non-uniformly sampled point clouds without normal information. In: Eurographics Symposium on Geometry Processing, vol. 1, Sardinia, Italy, June 2006, pp. 41–50 (2006)Google Scholar
  11. 11.
    Kolmogorov, V., Zabih, R.: Multi-camera Scene Reconstruction via Graph Cuts. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 82–96. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  12. 12.
    Kolmogorov, V., Zabih, R.: What energy functions can be minimized via graph cuts? IEEE Transactions on Pattern Analysis and Machine Intelligence 26(2), 147–159 (2004)CrossRefGoogle Scholar
  13. 13.
    Kolmogorov, V., Zabih, R., Gortler, S.J.: Generalized multi-camera scene reconstruction using graph cuts. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, Madison, USA, June 2003, pp. 501–516 (2003)Google Scholar
  14. 14.
    Kutulakos, K.N., Seitz, S.M.: A theory of shape by space carving. International Journal of Computer Vision 38(3), 199–218 (2000)CrossRefMATHGoogle Scholar
  15. 15.
    Levoy, M., Pulli, K., Curless, B., Rusinkiewicz, S., Koller, D., Pereira, L., Ginzton, M., Anderson, S., Davis, J., Ginsberg, J., Shade, J., Fulk, D.: The digital michelangelo project: 3d scanning of large statues. In: ACM SIGGRAPH, vol. 1, New Orleans, USA, July 2000, pp. 131–144. ACM Press, New York (2000)Google Scholar
  16. 16.
    Lorenson, W., Cline, H.: A high resolution 3d surface reconstruction algorithm. In: ACM SIGGRAPH, vol. 1, Anaheim, USA, July 1987, pp. 163–170. ACM Press, New York (1987)Google Scholar
  17. 17.
    Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision 47(1-3), 7–42 (2002)CrossRefMATHGoogle Scholar
  18. 18.
    Seitz, S., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: A comparison and evaluation of multi-view stereo reconstruction algorithms. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, New York, USA, June 2006, pp. 519–526 (2006)Google Scholar
  19. 19.
    Vogiatzis, G., Torr, P.H.S., Cipolla, R.: Multi-view stereo via volumetric graph-cuts. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, Washington D.C., USA, June 2005, pp. 391–398 (2005)Google Scholar
  20. 20.
    Wong, K.-Y., Cipolla, R.: Reconstruction of outdoor sculptures from silhouettes under approximate circular motion of an uncalibrated hand-held camera. IEEE Transactions on Information and Systems 87(1), 27–33 (2004)Google Scholar
  21. 21.
    Yang, R., Welch, G., Bishop, G.: Real-time consensus based scene reconstruction using commodity graphics hardware. In: Proceedings of Pacific Graphics, Beijing, China, October 2002, pp. 358–363 (2002)Google Scholar
  22. 22.
    Yezzi, A., Soatto, S.: Stereoscopic segmentation. International Journal of Computer Vision 53(1), 31–43 (2003)CrossRefMathSciNetGoogle Scholar
  23. 23.
    Zach, C., Sormann, M., Karner, K.: High performance multi-view reconstruction. In: 3DPVT, Chapel Hill, USA, CD Proceedings (June 2006)Google Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Mario Sormann
    • 1
  • Christopher Zach
    • 1
  • Joachim Bauer
    • 1
  • Konrad Karner
    • 1
  • Horst Bishof
    • 2
  1. 1.VRVis Research Center, Inffeldgasse 16, 8010 GrazAustria
  2. 2.Institute for Computer Graphics and Vision, Graz University of Technology, Inffeldgasse 16, 8010 GrazAustria

Personalised recommendations