Consistent Multi-view Reconstruction from Epipolar Geometries with Outliers

  • Daniel Martinec
  • Tomáš Pajdla
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)


This paper presents a method for automatic 3D-reconstruction from a set of images. The main contribution of this paper is a robust integration of the partial correspondences from image pairs provided by an existing correspondence estimator into a reconstruction consistent with all images of the scene. Projective shape and motion is estimated by factorization of a matrix containing the images of all scene points. Outlier detection is based on ransac paradigm and the trifocal tensors. Compared to previous methods, this method can handle perspective views, occlusions, and outliers in image correspondences jointly. The main novelty of this paper is the fusion of a correspondence estimator [9] for wide base-line stereo and the method for outlier detection [7]. It appears that the method is able to detect outliers that cannot be detected using the epipolar geometry alone and therefore it is suitable for integrating with wide base-line stereo from image pairs. The new method is demonstrated by experiments with laboratory and outdoor image sets and some results on metric reconstruction are shown.


  1. 1.
    V. Ferrari, T. Tuytelaars, and L. Van Gool. Wide-baseline multiple-view correspondences. In Proceedings of the CVPR, 2003. In print.Google Scholar
  2. 2.
    A. W. Fitzgibbon and A. Zisserman. Automatic camera recovery for closed or open image sequences. In Proc. ECCV, volume I, pages 311–326. Springer-Verlag, June 1998.Google Scholar
  3. 3.
    R. Hartley and A. Zisserman. Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge, UK, 2000.zbMATHGoogle Scholar
  4. 4.
    A. Heyden. Personal communication, 2002.Google Scholar
  5. 5.
    D. Q. Huynh and A. Heyden. Outlier detection in video sequences under affine projection. In Proc. IEEE Conf. on CVPR, pages 695–701, December 2001.Google Scholar
  6. 6.
    D. Jacobs. Linear fitting with missing data: Applications to structure from motion and to characterizing intensity images. In CVPR, pages 206–212, 1997.Google Scholar
  7. 7.
    D. Martinec and T. Pajdla. Outlier detection for factorization-based reconstruction from perspective images with occlusions. In Proceedings of the Photogrammetric Computer Vision, volume B, pages 161–164, 2002.Google Scholar
  8. 8.
    D. Martinec and T. Pajdla. Structure from many perspective images with occlusions. In Proceedings of the European Conference on Computer Vision, volume II, pages 355–369, Berlin, Germany, May 2002. Springer-Verlag.Google Scholar
  9. 9.
    J. Matas, O. Chum, M. Urban, and T. Pajdla. Robust wide baseline stereo from maximally stable extremal regions. In Proceedings of the British Machine Vision Conference, volume 1, pages 384–393, London, UK, September 2002. BMVA.Google Scholar
  10. 10.
    C. Rother and S. Carlsson. Linear multi view reconstruction with missing data. In Proceedings of the ECCV’02, volume II, pages 309–324, 2002.Google Scholar
  11. 11.
    P. Sturm and B. Triggs. A factorization based algorithm for multi-image projective structure and motion. In ECCV96(II), pages 709–720, 1996.Google Scholar
  12. 12.
    C. Tomasi and T. Kanade. Shape and motion from image streams under orthography: A factorization method. In IJCV(9), No. 2, pages 137–154, November 1992.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Daniel Martinec
    • 1
  • Tomáš Pajdla
    • 1
  1. 1.Center for Machine Perception, Department of Cybernetics Faculty of Elec. Eng.Czech Technical University in PraguePrahaCzech Republic

Personalised recommendations