Robust Variational Reconstruction from Multiple Views

  • Natalia Slesareva
  • Thomas Bühler
  • Kai Uwe Hagenburg
  • Joachim Weickert
  • Andrés Bruhn
  • Zachi Karni
  • Hans-Peter Seidel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4522)

Abstract

Recovering a 3-D scene from multiple 2-D views is indispensable for many computer vision applications ranging from free viewpoint video to face recognition. Ideally the recovered depth map should be dense, piecewise smooth with fine level of details, and the recovery procedure shall be robust with respect to outliers and global illumination changes. We present a novel variational approach that satisfies these needs. Our model incorporates robust penalisation in the data term and anisotropic regularisation in the smoothness term. In order to render the data term robust with respect to global illumination changes, a gradient constancy assumption is applied to logarithmically transformed input data. Focussing on translational camera motion and considering small baseline distances between the different camera positions, we reconstruct a common disparity map that allows to track image points throughout the entire sequence. Experiments on synthetic image data demonstrate the favourable performance of our novel method.

Keywords

computer vision variational methods multi-view reconstruction structure from motion partial differential equations 

References

  1. 1.
    Birkbeck, N., Cobzas, D., Sturm, P., Jagersand, M.: Variational Shape and Reflectance Estimation Under Changing Light and Viewpoints. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 536–549. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  2. 2.
    Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High Accuracy Optical Flow Estimation Based on a Theory for Warping. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3024, pp. 25–36. Springer, Heidelberg (2004)Google Scholar
  3. 3.
    Bruhn, A., Weickert, J., Kohlberger, T., Schnörr, C.: A multigrid platform for real-time motion computation with discontinuity-preserving variational methods. International Journal of Computer Vision 70(3), 257–277 (2006)CrossRefGoogle Scholar
  4. 4.
    Elsgolc, L.E.: Calculus of Variations. Pergamon, Oxford (1961)MATHGoogle Scholar
  5. 5.
    Faugeras, O., Keriven, R.: Variational principles, surface evolution, PDE’s, level set methods, and the stereo problem. IEEE Transactions on Image Processing 7(3), 336–344 (1998)MATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Furukawa, Y., Ponce, J.: Carved visual hulls for image-based modeling. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 564–577. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  7. 7.
    Huber, P.J.: Robust Statistics. Wiley, New York (1981)MATHGoogle Scholar
  8. 8.
    Pons, R.K.J.-P., Faugeras, O.: Modelling dynamic scenes by registering multi-view image sequences. In: International Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 822–827 (2005)Google Scholar
  9. 9.
    Jin, H., Yezzi, A.J., Soatto, S.: Variational multiframe stereo in the presence of specular reflections. In: Proceedings of the 1st International Symposium on 3D Data Processing Visualization and Transmission, June 2002, pp. 626–631 (2002)Google Scholar
  10. 10.
    Kolmogorov, V., Zabih, R.: Computing visual correspondences with occlusions using graph cut methods. In: Proc. Eighth International Conference on Computer Vision, vol. 2, Vancouver, Canada, July 2001, pp. 588–594. IEEE Computer Society Press, Los Alamitos (2001)Google Scholar
  11. 11.
    Li, G., Zucker, S.W.: Differential geometric consistency extends stereo to curved surfaces. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3953, pp. 44–57. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  12. 12.
    Nagel, H.-H., Enkelmann, W.: An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences. IEEE Transactions on Pattern Analysis and Machine Intelligence 8, 565–593 (1986)CrossRefGoogle Scholar
  13. 13.
    Pressigout, M., Marchand, E.: Model-free augmented reality by virtual visual servoing. In: IAPR Int. Conf. on Pattern Recognition, ICPR’04, vol. 2, Cambridge, UK, August 2004, pp. 887–891 (2004)Google Scholar
  14. 14.
    Stricker, D.: Tracking with reference images: A real-time and markerless tracking solution for out-door augmented reality applications. In: Virtual Reality, Archaeology, and Cultural Heritage International Symposium (VAST01), Glyfada, Greece (November 2001)Google Scholar
  15. 15.
    Yezzi, A.J., Soatto, S.: Structure from motion for scenes without features. In: Proc. 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, June 2003, pp. 525–532. IEEE Computer Society Press, Los Alamitos (2003)CrossRefGoogle Scholar
  16. 16.
    Young, D.M.: Iterative Solution of Large Linear Systems. Dover, New York (2003)MATHGoogle Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Natalia Slesareva
    • 1
  • Thomas Bühler
    • 1
  • Kai Uwe Hagenburg
    • 1
  • Joachim Weickert
    • 1
  • Andrés Bruhn
    • 1
  • Zachi Karni
    • 2
  • Hans-Peter Seidel
    • 2
  1. 1.Mathematical Image Analysis Group, Dept. of Mathematics and Computer Science, Saarland University, Building E1.1, 66041 SaarbrückenGermany
  2. 2.Max-Planck-Institut für Informatik, Stuhlsatzenhausweg 85, 66123 SaarbrückenGermany

Personalised recommendations