Resampling Structure from Motion

  • Tian Fang
  • Long Quan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6312)

Abstract

This paper proposes a hierarchical framework that resamples 3D reconstructed points to reduce computation cost on time and memory for very large-scale Structure from Motion. The goal is to maintain accuracy and stability similar for different resample rates. We consider this problem in a level-of-detail perspective, from a very large scale global and sparse bundle adjustment to a very detailed and local dense optimization. The dense matching are resampled by exploring the redundancy using local invariant properties, while 3D points are resampled by exploring the redundancy using their covariance and their distribution in both 3D and image space. Detailed experiments on our resample framework are provided. We also demonstrate the proposed framework on large-scale examples. The results show that the proposed resample scheme can produce a 3D reconstruction with the stability similar to quasi dense methods, while the problem size is as neat as sparse methods.

Keywords

Local Group Camera Motion Local Geometry Merging Process Bundle Adjustment 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Pollefeys, M., Nistér, D., Frahm, J., Akbarzadeh, A., Mordohai, P., Clipp, B., Engels, C., Gallup, D., Kim, S., Merrell, P., Salmi, C., Sinha, S., Talton, B., Wang, L., Yang, Q., Stewénius, H., Yang, R., Welch, G., Towles, H.: Detailed real-time urban 3D reconstruction from video. IJCV 78, 143–167 (2008)CrossRefGoogle Scholar
  2. 2.
    Quan, L.: Invariants of six points and projective reconstruction from three uncalibrated images. IEEE PAMI 17, 34–46 (1995)Google Scholar
  3. 3.
    Nistér, D.: Reconstruction from uncalibrated sequences with a hierarchy of trifocal tensors. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 649–663. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  4. 4.
    Snavely, N., Seitz, S.M., Szeliski, R.: Photo tourism: Exploring photo collections in 3D. ACM Trans. Graph. 25, 835–846 (2006)CrossRefGoogle Scholar
  5. 5.
    Triggs, B., McLauchlan, P.F., Hartley, R.I., Fitzgibbon, A.W.: Bundle adjustment - a modern synthesis. In: Triggs, B., Zisserman, A., Szeliski, R. (eds.) ICCV-WS 1999. LNCS, vol. 1883, pp. 298–372. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  6. 6.
    Lhuillier, M., Quan, L.: A quasi-dense approach to surface reconstruction from uncalibrated images. IEEE PAMI 27, 418–433 (2005)Google Scholar
  7. 7.
    Nistér, D.: Frame decimation for structure and motion. In: Pollefeys, M., Van Gool, L., Zisserman, A., Fitzgibbon, A.W. (eds.) SMILE 2000. LNCS, vol. 2018, pp. 17–34. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  8. 8.
    Snavely, N., Seitz, S., Szeliski, R.: Skeletal graphs for efficient structure from motion. In: CVPR, pp. 1–8 (2008)Google Scholar
  9. 9.
    Ni, K., Steedly, D., Dellaert, F.: Out-of-core bundle adjustment for large-scale 3D reconstruction. In: ICCV, pp. 1–8 (2007)Google Scholar
  10. 10.
    Mouragnon, E., Dekeyser, F., Sayd, P., Lhuillier, M., Dhome, M.: Real time localization and 3D reconstruction. In: CVPR, vol. 1, pp. 363–370 (2006)Google Scholar
  11. 11.
    Eudes, A., Lhuillier, M.: Error propagations for local bundle adjustment. In: CVPR Workshops, pp. 2411–2418 (2009)Google Scholar
  12. 12.
    Seitz, S., 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
  13. 13.
    Morris, D.D.: Gauge Freedoms and Uncertainty Modeling for Three-dimensional Computer Vision. PhD thesis, Carnegie Mellon University (2001)Google Scholar
  14. 14.
    Lowe, D.: Object recognition from local scale-invariant features. In: ICCV, pp. 1150–1157 (1999)Google Scholar
  15. 15.
    Levinshtein, A., Stere, A., Kutulakos, K., Fleet, D., Dickinson, S., Siddiqi, K.: TurboPixels: fast superpixels using geometric flows. IEEE PAMI 31, 2290–2297 (2009)Google Scholar
  16. 16.
    Baker, J.: Reducing bias and inefficiency in the selection algorithm. In: Proceedings of the Second International Conference on Genetic Algorithms on Genetic Algorithms and Their Application Table of Contents, pp. 14–21. L. Erlbaum Assoiates Inc., Hillsdale (1987)Google Scholar
  17. 17.
    Lhuillier, M., Quan, L.: Robust dense matching using local and global geometric constraints. In: ICPR, pp. 968–972 (2000)Google Scholar
  18. 18.
    Lhuillier, M., Quan, L.: Match propagation for image-based modeling and rendering. IEEE PAMI 24, 1140–1146 (2002)Google Scholar
  19. 19.
    Nistér, D.: An efficient solution to the five-point relative pose problem. IEEE PAMI 26, 756–777 (2004)Google Scholar
  20. 20.
    Lourakis, M.A., Argyros, A.: SBA: A software package for generic sparse bundle adjustment. ACM Trans. Math. Software 36, 1–30 (2009)CrossRefGoogle Scholar
  21. 21.
    Xiao, J., Fang, T., Zhao, P., Lhuillier, M., Quan, L.: Image-based street-side city modeling. ACM Trans. Graph. 28, 114:1–114:12 (2009)Google Scholar
  22. 22.
    Agarwal, S., Snavely, N., Simon, I., Seitz, S.M., Szeliski, R.: Building rome in a day. In: ICCV, pp. 72–79 (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Tian Fang
    • 1
  • Long Quan
    • 1
  1. 1.The Hong Kong University of Science and TechnologyHong KongChina

Personalised recommendations