Dense depth map reconstruction: A minimization and regularization approach which preserves discontinuities

  • Luc Robert
  • Rachid Deriche
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1064)


We present a variational approach to dense stereo reconstruction which combines powerful tools such as regularization and multi-scale processing to estimate directly depth from a number of stereo images, while preserving depth discontinuities. The problem is set as a regularization and minimization of a nonquadratic functional. The Tikhonov quadratic regularization term usually used to recover smooth solution is replaced by a function of the gradient depth specifically derived to allow depth discontinuities formation in the solution. Conditions to be fulfilled by this specific regularizing term to preserve discontinuities are also presented. To solve this problem in the discrete case, a PDE-based explicit scheme for moving iteratively towards the solution has been developed. This approach presents the additional advantages of not introducing any intermediate representation such as disparity or rectified images: depth is computed directly from the grey-level images and we can also deal with any number (greater than two) of cameras. Promising experimental results illustrate the capabilities of this approach.


Stereo Image Stereo Match Epipolar Line Depth Discontinuity Inhomogeneous Region 
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.


  1. 1.
    L. Alvarez, P.L. Lions, and J.M. Morel. Image selective smoothing and edge detection by nonlinear diffusion (ii). SIAM J, Numer Anal, 29(3):845–866, 1992.Google Scholar
  2. 2.
    L. Alvarez and F. Morales. Affine multiscale analysis of corners. Prepublicacion, Ref: 9402, Universidad de Las Palmas de Gran Canaria, 1994.Google Scholar
  3. 3.
    G. Aubert and L. Lazaroaia. A variational method in image recovery. TR 423, URA au CNRS no 168,laboratoire J-A Dieudonne, Université de Nice Sophia-Antipolis-CNRS, June 1995.Google Scholar
  4. 4.
    N. Ayache and B. Faverjon. Efficient Registration Of Stereo Images by Matching Graph Descriptions of Edge Segments. The Int'l Journal of Comp. Vision, 1(2): 107–131, April 1987.Google Scholar
  5. 5.
    N. Ayache and C. Hansen. Rectification of Images for Binocular and Trinocular Stereovision. In Proc. Int'l Conf. on Pattern Recognition, pages-, October 1988. 9th, Rome, Italy.Google Scholar
  6. 6.
    S.T. Barnard. Stochastic Stereo Matching Over Scale. The Int'l Journal of Comp. Vision, 3(1): 17–32, May 1989.Google Scholar
  7. 7.
    L. Blanc-Ferraud, P. Charbonnier, G. Aubert, and M. Barlaud. Nonlinear image processing: Modeling and fast algorithm for regularization with edge detection. TR 1, Laboratoire I3S, URA 1376 du CNRS, Université de Nice Sophia-Antipolis-CNRS, Janvier 1995.Google Scholar
  8. 8.
    A.T. Brint and M. Brady. Stereo Matching of Curves. In IARP — 1st Int'l Workshop on Multi-sensor Fusion and Environment Modelling, October 1989.Google Scholar
  9. 9.
    P. Charbonnier. Reconstruction d'image: Régularisation avec prise en compte des discontinuités. Thèse, Université of Nice Sophia-Antipolis, September 1994.Google Scholar
  10. 10.
    P. Charbonnier, G. Aubert, M. Blanc-Ferraud, and M. Barlaud. Two-Deterministic Half-Quadratic Regularizatiob Algorithms for Computed Imaging. In Proc. IEEE Int. Conf. on Image Proc. ICIP, volume II of III, pages 168–172, Austin(Texas), November 13–16 1994.Google Scholar
  11. 11.
    P. Delacourt. Applications des EDP en Analyse Multi-Echelle et en Traitement d'Images. Rapport de stage de DEA. proposé et encadré par R. Deriche, INRIA, Université Nice-Sophia Antipolis, France, Juin 1995.Google Scholar
  12. 12.
    R. Deriche and O. Faugeras. Les EDP en traitement des images et vision par ordinateur. Technical Report 2697, INRIA, November 1995.Google Scholar
  13. 13.
    P. Fua. Combining Stereo and Monocular Information to Compute Dense Depth Maps that Preserve Depth Discontinuities. In Proc. Int'l Joint Conf. on Artificial Intelligence, pages-, Sydney, Australia, August 1991.Google Scholar
  14. 14.
    S. Geman and G. Reynolds. Constrained Restauration and the Recovery of discontinuities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 14, 1992.Google Scholar
  15. 15.
    P.J. Green. Bayesian Reconstruction From Emission Tomography Data Using A Modified EM Algorithm. IEEE Trans. Med. Imaging, MI-9, 1990.Google Scholar
  16. 16.
    P Kornprobst. Calcul de Flot Optique avec Préservation des Discontinuités. Rapport de stage de DEA. Proposé et encadré par R. Deriche et G. Aubert, INRIA, Université Nice-Sophia Antipolis, France, Juin 1995.Google Scholar
  17. 17.
    F. Lustman. Vision Stéréoscopique Et Perception Du Mouvement En Vision Artificielle. PhD thesis, Université de Paris-Sud Centre d'Orsay, December 1988.Google Scholar
  18. 18.
    A. Meygret, M. Thonnat, and M. Berthod. A Pyramidal Stereovision Algorithm Based on Contour Chain Points. In Proc. European Conf. on Comp. Vision, Antibes, France, April 1990. Springer Verlag.Google Scholar
  19. 19.
    H.K. Nishihara and T. Poggio. Stereo Vision for Robotics. In Int'l Symposium on Robotics Research, Bretton Woods, New Hampshire, 1983.Google Scholar
  20. 20.
    Y. Ohta and T. Kanade. Stereo by Intra-and Inter-Scanline Search. IEEE Transactions on Pattern Analysis and Machine Intelligence, 7, No 2:139–154, 1985.Google Scholar
  21. 21.
    S. Osher and L. Rudin. Shocks and Other Nonlinear Filtering Applied to Image Processing. In Proc SPIE Vol 1567: Applications of Digital Image Processing XIV, pages 414–431, San-Diego, 1991.Google Scholar
  22. 22.
    P. Perona and J. Malik. Scale-space and edge detection using anisotropic diffusion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(7):629–639, 1990.Google Scholar
  23. 23.
    S.B. Pollard, J.E.W. Mayhew, and J.P. Frisby. PMF: a Stereo Correspondance Algorithm using a Disparity Gradient Limit. Perception, 14:449–470, 1985.Google Scholar
  24. 24.
    L Robert. Camera calibration without feature extraction. Computer Vision, Graphics, and Image Processing, 1995. to appear, also INRIA Technical Report 2204.Google Scholar
  25. 25.
    L. Robert and O.D. Faugeras. Curve-Based Stereo: Figural Continuity And Curvature. In Proc. Int'l Conf. on Comp. Vision and Pattern Recognition, pages 57–62, Maui, Hawai, June 1991. IEEE.Google Scholar
  26. 26.
    L. Rudin, S. Osher, and E. Fatemi. Nonlinear total variation based noise removal algorithms. Physica D, 60:259–268, 1992.Google Scholar
  27. 27.
    D. Terzopoulos. Image Analysis Using Multigrid Relaxation Methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(2):129–139, March 1986.Google Scholar
  28. 28.
    A.N. Tikhonov and V.Y. Arsenin. In Solutions of Ill-Posed Problems. Wiley, New-York, 1977.Google Scholar
  29. 29.
    G. Toscani. Systèmes de Calibration et Perception du Mouvement en Vision Artificielle. PhD thesis, Université de Paris-Sud Centre d'Orsay, December 1987.Google Scholar
  30. 30.
    N. Yokoya. Stereo Surface Reconstruction by Multiscale-Multistage Regularization. Technical Report TR-90-45, ETL Electrotechnical Laboratory, November 1990.Google Scholar
  31. 31.
    Y.L. You, M. Kaveh, W.Y. Xu, and A. Tannenbaum. Analysis and Design of Anisotropic Diffusion for Image Processing. In Proc. IEEE Int. Conf. on Image Proc. ICIP-94, volume II of III, pages 497–501, Austin(Texas), November 13–16 1994.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Luc Robert
    • 1
  • Rachid Deriche
    • 1
  1. 1.INRIASophia-AntipolisFrance

Personalised recommendations