Advertisement

Hallucination-Free Multi-View Stereo

  • Michal Jancosek
  • Tomas Pajdla
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6554)

Abstract

We present a multi-view stereo method that avoids producing hallucinated surfaces which do not correspond to real surfaces. Our approach to 3D reconstruction is based on the minimal s-t cut of the graph derived from the Delaunay tetrahedralization of a dense 3D point cloud, which produces water-tight meshes. This is often a desirable property but it hallucinates surfaces in complicated scenes with multiple objects and free open space. For example, a sequence of images obtained from a moving vehicle often produces meshes where the sky is hallucinated because there are no images looking from the above to the ground plane. We present a method for detecting and removing such surfaces. The method is based on removing perturbation sensitive parts of the reconstruction using multiple reconstructions of perturbed input data. We demonstrate our method on several standard datasets often used to benchmark multi-view stereo and show that it outperforms the state-of-the-art techniques .

Keywords

multi-view stereo stereo 3D reconstruction 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Vu, H., Keriven, R., Labatut, P., Pons, J.P.: Towards high-resolution large-scale multi-view stereo. In: CVPR (2009)Google Scholar
  2. 2.
    Bradley, D., Boubekeur, T., Heidrich, W.: Accurate multi-view reconstruction using robust binocular stereo and surface meshing. In: CVPR, pp. 1–8 (2008)Google Scholar
  3. 3.
    Zaharescu, A., Boyer, E., Horaud, R.: TransforMesh: A Topology-Adaptive Mesh-Based Approach to Surface Evolution. In: Yagi, Y., Kang, S.B., Kweon, I.S., Zha, H. (eds.) ACCV 2007, Part II. LNCS, vol. 4844, pp. 166–175. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  4. 4.
    Labatut, P., Pons, J., Keriven, R.: Efficient multi-view reconstruction of large-scale scenes using interest points, delaunay triangulation and graph cuts. In: ICCV, pp. 1–8 (2007)Google Scholar
  5. 5.
    Campbell, N.D.F., Vogiatzis, G., Hernández, C., Cipolla, R.: Using Multiple Hypotheses to Improve Depth-Maps for Multi-View Stereo. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 766–779. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  6. 6.
    Goesele, M., Snavely, N., Curless, B., Hoppe, H., Seitz, S.: Multi-view stereo for community photo collections. In: ICCV (2007)Google Scholar
  7. 7.
    Furukawa, Y., Ponce, J.: Accurate, dense, and robust multi-view stereopsis. In: CVPR, pp. 1–8 (2007)Google Scholar
  8. 8.
    Seitz, S.M., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: A comparison and evaluation of multi-view stereo reconstruction algorithms. In: CVPR, pp. 519–528 (2006)Google Scholar
  9. 9.
    Strecha, C., von Hansen, W., Van Gool, L., Fua, P., Thoennessen, U.: On benchmarking camera calibration and multi-view stereo for high resolution imagery. In: CVPR, pp. 1–8 (2008)Google Scholar
  10. 10.
    Labatut, P., Pons, J., Keriven, R.: Robust and efficient surface reconstruction from range data. In: Computer Graphics Forum (2009)Google Scholar
  11. 11.
    Kazhdan, M., Bolitho, M., Hoppe, H.: Poisson surface reconstruction. In: SGP 2006, pp. 61–70 (2006)Google Scholar
  12. 12.
    Ford, L.R., Fulkerson, D.R.: Flows in Networks. Princeton University Press (1962)Google Scholar
  13. 13.
    Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Transactions on Pattern Analysis and Machine Intelligence 26, 1124–1137 (2004)CrossRefGoogle Scholar
  14. 14.
    Jancosek, M., Shekhovtsov, A., Pajdla, T.: Scalable multi-view stereo. In: 3DIM (2009)Google Scholar
  15. 15.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)CrossRefGoogle Scholar
  16. 16.
  17. 17.
    Gallup, D., Frahm, J., Mordohai, P., Yang, Q., Pollefeys, M.: Real-time plane-sweeping stereo with multiple sweeping directions. In: CVPR, pp. 1–8 (2007)Google Scholar
  18. 18.
    Yang, R., Pollefeys, M.: Multi-resolution real-time stereo on commodity graphics hardware. In: CVPR, pp. I: 211–I: 217 (2003)Google Scholar
  19. 19.
    Collins, R.: A space-sweep approach to true multi-image matching. Technical Report UM-CS-1995-101 (1995)Google Scholar
  20. 20.
    Salman, N., Yvinec, M.: Surface reconstruction from multi-view stereo. In: Modeling-3D (2009)Google Scholar
  21. 21.
    Strecha, C., Fransens, R., Van Gool, L.: Wide-baseline stereo from multiple views: a probabilistic account. In: CVPR (2004)Google Scholar
  22. 22.

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Michal Jancosek
    • 1
  • Tomas Pajdla
    • 1
  1. 1.Center for Machine Perception, Department of Cybernetics Faculty of Elec. Eng.Czech Technical University in PragueCzech Republic

Personalised recommendations