3D Geometry from Uncalibrated Images

  • George Kamberov
  • Gerda Kamberova
  • O. Chum
  • Š. Obdržálek
  • D. Martinec
  • J. Kostková
  • T. Pajdla
  • J. Matas
  • R. Šára
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4292)


We present an automatic pipeline for recovering the geometry of a 3D scene from a set of unordered, uncalibrated images. The contributions in the paper are the presentation of the system as a whole, from images to geometry, the estimation of the local scale for various scene components in the orientation-topology module, the procedure for orienting the cloud components, and the method for dealing with points of contact. The methods are aimed to process complex scenes and non-uniformly sampled, noisy data sets.


Point Cloud Tangent Plane Data Pipeline Dense Match Cloud Component 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Alexa, M., Behr, J., Cohen-Or, D., Fleishman, S., Levin, D., Silva, C.T.: Computing and Rendering Point Set Surfaces. Trans. Vis. Comp. Graph. 9(1), 3–15 (2003)CrossRefGoogle Scholar
  2. 2.
    Amenta, N., Kill, Y.J.: Defining Point-Set Surfaces. ACM Trans. on Graphics 23(3), 264–270 (2004); Special Issue: Proceedings of SIGGRAPH 2004CrossRefGoogle Scholar
  3. 3.
    Boyer, E., Petitjean, S.: Regular and Non-Regular Point Sets: Properties and Reconstruction. Comp. Geometry 19, 101–131 (2001)MATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Hartley, R.: Theory and Practice of Projective Rectification. Int. J. Computer Vision 35(2), 115–127 (1999)CrossRefMathSciNetGoogle Scholar
  5. 5.
    Hartley, R., Zisserman, A.: Multiple View GeomeLtry in Computer Vision. Cambridge University Press, Cambridge (2000)Google Scholar
  6. 6.
    Chum, O., Matas, J., Kittler, J.: Locally optimized RANSAC. In: Michaelis, B., Krell, G. (eds.) DAGM 2003. LNCS, vol. 2781, pp. 236–243. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  7. 7.
    Chum, O., Werner, T., Matas, J.: Two-view geometry estimation unaffected by a dominant plane. In: CVPR, vol. 1, pp. 772–779 (2005)Google Scholar
  8. 8.
    Cornelius, H., Šára, R., Martinec, D., Pajdla, T., Chum, O., Matas, J(G.): Towards Complete Free-Form Reconstruction of Complex 3D Scenes from an Unordered Set of Uncalibrated Images. In: Comaniciu, D., Mester, R., Kanatani, K., Suter, D. (eds.) SMVP 2004. LNCS, vol. 3247, pp. 1–12. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  9. 9.
    Cornelis, K., Verbiest, F., Van Gool, L.J.: Drift detection and removal for sequential structure from motion algorithms. PAMI 26(10), 1249–1259 (2004)Google Scholar
  10. 10.
    Dey, T.K., Sun, J.: Extremal Surface Based Projections Converge and Reconstruct with Isotopy, Tech. Rep. OSU-CISRC-05-TR25 (April 2005)Google Scholar
  11. 11.
    Edelsbrunner, H., Mucke, E.P.: Three-dimensional alpha shapes. ACM Trans. Graph. 13(10), 43–72 (1994)MATHCrossRefGoogle Scholar
  12. 12.
    Gopi, M., Krishnan, S., Silva, C.T.: Surface reconstruction based on lower dimensional localized Delaunay triangulation. In: EUROGRAPHICS 2000, Computer Graphics Forum, vol. 19(3) (2000)Google Scholar
  13. 13.
    Guillemaut, J.-Y., Drbohlav, O., Sara, R., Illingworth, J.: Helmholtz Stereopsis on rough and strongly textured surfaces. In: 2nd Intl. Symp. 3DPVT, Greece (2004)Google Scholar
  14. 14.
    Hoppe, H., De Rose, T., Duchamp, T., McDonald, J., Stuetzle, W.: Surface reconstruction from unorganized points. Comp. Graph (SIGGRAPH 1992 Proceedings) 26, 71–78 (1992)CrossRefGoogle Scholar
  15. 15.
    Kahl, F.: Multiple view geometry and the l  ∞ -norm. In: ICCV 2005, pp. II: 1002–1009 (2005)Google Scholar
  16. 16.
    Kamberov, G., Kamberova, G.: Conformal Method for Quantitative Shape Extraction: Performance Evaluation. In: ICPR 2004, IEEE Proceedings Series, Cambridge (August 2004)Google Scholar
  17. 17.
    Kamberov, G., Kamberova, G.: Topology and Geometry of Unorganized Point Clouds. In: 2nd Intl. Symp. 3D Data processing, Visualization and Transmission, Thessaloniki, Greece. IEEE Proc. Series, in cooperation with Eurographics and ACM SIGGRAPH (2004)Google Scholar
  18. 18.
    Kamberov, G., Kamberova, G., Jain, A.: 3D shape from unorganized 3D point clouds. In: Bebis, G., Boyle, R., Koracin, D., Parvin, B. (eds.) ISVC 2005. LNCS, vol. 3804, pp. 621–629. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  19. 19.
    Kamberov, G., Norman, P., Pedit, F., Pinkall, U.: Quaternions, Spinors, and Surfaces. American Mathematical Society (2002) ISBN 0821819283Google Scholar
  20. 20.
    Kostková, J., Šára, R.: Stratified Dense Matching for Stereopsis in Complex Scenes. In: Proc. BMVC, vol. 1 (2003)Google Scholar
  21. 21.
    Kostková, J., Čech, J., Šára, R.: Dense Stereomatching Algorithm Performance for View Prediction and Structure Reconstruction. In: Bigun, J., Gustavsson, T. (eds.) SCIA 2003. LNCS, vol. 2749, pp. 101–107. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  22. 22.
    Lalonde, J., Unnikrishnan, R., Vandapel, N., Hebert, M.: Fifth Scale Selection for Classification of Point-sampled 3-D Surfaces. In: Proc. International Conference on 3-D Digital Imaging and Modeling (3DIM 2005) (2005)Google Scholar
  23. 23.
    Martinec, D., Pajdla, T.: 3D Reconstruction by Fitting Low-rank Matrices with Missing Data. In: Proc CVPR 2005, vol. I, pp. 198–205 (2005)Google Scholar
  24. 24.
    Martinec, D., Pajdla, T.: 3D reconstruction by gluing pair-wise euclidean reconstructions, or how to achieve a good reconstruction from bad images. In: 3DPVT, p. 8. University of North Carolina, Chapel Hill (2006)Google Scholar
  25. 25.
  26. 26.
    Matas, J., Obdržálek, Š., Chum, O.: Local affine frames for wide-baseline stereo. In: ICPR(4), pp. 363–366 (2002)Google Scholar
  27. 27.
    Mikolajczyk, K., et al.: A Comparison of Affine Region Detectors. IJCV (2005)Google Scholar
  28. 28.
    Mitra, N., Nguyen, N., Guibas, L.: Estimating surface normals in noisy point cloud data. International Journal of Computational Geometry & Applications 14(4&5), 261–276 (2004)MATHCrossRefMathSciNetGoogle Scholar
  29. 29.
    Nistér, D.: An efficient solution to the five-point relative pose. PAMI 26(6), 756–770 (2004)Google Scholar
  30. 30.
    Pollefeys, M., et al.: Image-based 3d recording for archaeological field work. CG&A 23(3), 20–27 (2003)Google Scholar
  31. 31.
    Šára, R.: Accurate Natural Surface Reconstruction from Polynocular Stereo. In: Proc. NATO Adv. Res. Workshop Confluence of Computer Vision and Computer Graphics. NATO Science Series, (84), pp. 69–86. Kluwer, Dordrecht (2000)Google Scholar
  32. 32.
    Šára, R., Bajcsy, R.: Fish-Scales: Representing Fuzzy Manifolds. In: Proc. Int. Conf. on Computer Vision. Narosa Publishing House, Bombay (1998)Google Scholar
  33. 33.
    Sim, K., Hartley, R.: Recovering camera motion using l  ∞  minimization. In: CVPR, New York, USA, vol. 1, pp. 1230–1237 (June 2006)Google Scholar
  34. 34.
    Stewénius, H., Nistér, D., Kahl, F., Schaffalitzk, F.: A minimal solution for relative pose with unknown focal length. In: CVPR, vol. 2, pp. 789–794 (2005)Google Scholar
  35. 35.
    Surazhsky, T., Magid, E., Soldea, O., Elber, G., Rivlin, E.: A comparison of Gaussian and mean curvatures estimation methods on triangular meshes. In: 2003 IEEE Interntl. Conf. on Robotics & Automation (ICRA 2003) (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • George Kamberov
    • 1
  • Gerda Kamberova
    • 2
  • O. Chum
    • 3
  • Š. Obdržálek
    • 3
  • D. Martinec
    • 3
  • J. Kostková
    • 3
  • T. Pajdla
    • 3
  • J. Matas
    • 3
  • R. Šára
    • 3
  1. 1.Stevens Institute of TechnologyHobokenUSA
  2. 2.Hofstra UniversityHempsteadUSA
  3. 3.Center for Machine Perception, Department of Cybernetics, Faculty of Electrical EngineeringCzech Technical UniversityPrague 6Czech Republic

Personalised recommendations