Abstract
This paper addresses the problem of estimating the 3D shape of a smooth textureless solid from multiple images acquired under orthographic projection from unknown and unconstrained viewpoints. In this setting, the only reliable image features are the object’s silhouettes, and the only true stereo correspondence between pairs of silhouettes are the frontier points where two viewing rays intersect in the tangent plane of the surface. An algorithm for identifying geometrically-consistent frontier points candidates while estimating the cameras’ projection matrices is presented. This algorithm uses the signature representation of the dual of image silhouettes to identify promising correspondences, and it exploits the redundancy of multiple epipolar geometries to retain the consistent ones. The visual hull of the observed solid is finally reconstructed from the recovered viewpoints. The proposed approach has been implemented, and experiments with six real image sequences are presented, including a comparison between ground-truth and recovered camera configurations, and sample visual hulls computed by the algorithm.
Chapter PDF
References
Sethi, A., Renaudie, D., Kriegman, D., Ponce, J.: Curve and Surface Duals and the Recognition of Curved 3D Objects from their Silhouette. Int. J. of Comp. Vision 58(1) (2004)
Åström, K., Kahl, F.: Motion estimation in image sequences using the deformation of apparent contours. IEEE Trans. Patt. Anal. Mach. Intell 21(2), 114–127 (1999)
Baumgart, B.G.: Geometric modeling for computer vision. Technical Report AIM- 249, Stanford University, Ph.D. Thesis. Department of Computer Science (1974)
Birchfield, S.: KLT: An implementation of the Kanade-Lucas-Tomasi feature tracker
Boyer, E., Berger, M.O.: 3d surface reconstruction using occluding contours. Int. J. of Comp. Vision 22(3), 219–233 (1997)
Cipolla, R., Åström, K.E., Giblin, P.J.: Motion from the frontier of curved surfaces. In: Proc. Int. Conf. Comp. Vision, pp. 269–275 (1995)
Cipolla, R., Blake, A.: Surface shape from the deformation of apparent contours. Int. J. of Comp. Vision 9(2), 83–112 (1992)
Faugeras, O., Luong, Q.-T., Papadopoulo, T.: The Geometry of Multiple Images. MIT Press, Cambridge (2001)
Forsyth, D.A., Ponce, J.: Computer Vision: A Modern Approach. Prentice-Hall, Englewood Cliffs (2002)
Giblin, P., Weiss, R.: Epipolar curves on surfaces. Image and Vision Computing 13(1), 33–44 (1995)
Giblin, P., Pollick, F.E., Rycroft, J.E.: Recovery of an unknown axis of rotation from the profiles of a rotating surface. Journal of Optical Society America, 1976–1984 (1994)
Giblin, P., Weiss, R.: Reconstruction of surface from profiles. In: Proc. Int. Conf. Comp. Vision, pp. 136–144 (1987)
Hartley, R., Zisserman, A.: Multiple view geometry in computer vision. Cambridge University Press, Cambridge (2000)
Joshi, T., Ahuja, N., Ponce, J.: Structure and motion estimation from dynamic silhouettes under perspective projection. In: Proc. Int. Conf. Comp. Vision, pp. 290–295 (1995)
Koenderink, J.J.: What does the occluding contour tell us about solid shape? Perception 13, 321–330 (1984)
Laurentini. How far 3D shapes can be understood from 2D silhouettes. IEEE Trans. Patt. Anal. Mach. Intell., 17(2):188–194, February 1995.
Levi, N., Werman, M.: The viewing graph. In: IEEE Int. Conf. on Computer Vision and Pattern Recognition, pp. 518–522 (2003)
Mendonca, P., Wong, K.-Y.K., Cipolla, R.: Camera pose estimation and reconstruction from image profiles under circular motion. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 864–877. Springer, Heidelberg (2000)
Poelman, C.J., Kanade, T.: A paraperspective factorization method for shape and motion recovery. IEEE Trans. Patt. Anal. Mach. Intell. 19(3), 206–218 (1997)
Szeliski, R., Weiss, R.: Robust shape recovery from occluding contours using a linear smoother. Int. J. of Comp. Vision 28(1), 27–44 (1998)
Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: a factorization method. Int. J. of Comp. Vision 9(2), 137–154 (1992)
Torr, P., Murray, D.: The development and comparison of robust methods for estimating the fundamental matrix. Int. J. of Comp. Vision 24(3) (1997)
Torr, P.H., Zisserman, A., Maybank, S.J.: Robust detection of degenerate configurations for the fundamental matrix. In: Proc. Int. Conf. Comp. Vision, Boston, MA, pp. 1037–1042 (1995)
Torr, P.H.S., Zisserman, A.: Mlesac: A new robust estimator with application to estimating image geometry. CVIU 78(1), 138–156 (2000)
Vaillant, R., Faugeras, O.D.: Using extremal boundaries for 3-d object modeling. IEEE Trans. Patt. Anal. Mach. Intell. 14(2), 157–173 (1992)
Vijayakumar, B., Kriegman, D.J., Ponce, J.: Structure and motion of curved 3d objects from monocular silhouettes. In: IEEE Int. Conf. on Computer Vision and Pattern Recognition, pp. 327–334 (1996)
Wang, Y., Teoh, E.K., Shen, D.: Structure-adaptive b-snake for segmenting complex objects. In: IEEE International Conference on Image Processing (2001)
Wong, K.-Y.K., Cipolla, R.: Structure and motion from silhouettes. In: Proc. Int. Conf. Comp. Vision, pp. 217–222 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Furukawa, Y., Sethi, A., Ponce, J., Kriegman, D. (2004). Structure and Motion from Images of Smooth Textureless Objects. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3022. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24671-8_23
Download citation
DOI: https://doi.org/10.1007/978-3-540-24671-8_23
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21983-5
Online ISBN: 978-3-540-24671-8
eBook Packages: Springer Book Archive