Abstract
In the process of digitizing the geometry and appearance of 3D objects, texture registration is a necessary step that solves the 2D–3D mapping between the 2D texture images and the 3D geometric model. For evaluation of texture registration with ground truth, accurate datasets can be obtained with a complex setup consisting of calibrated geometry and texture capture devices. We do not have any knowledge of such evaluation performed; current evaluations reflect, at their best, the precision achieved by the algorithms, but fail to identify a possible bias. We propose a new evaluation measure based on the epipolar geometry of texture image pairs, with the advantage that the ground truth can be extracted solely from the texture images, independent of the 3D acquisition. We developed a noise model suitable to our purpose and analysed three distance measures based on epipolar geometry, well known in the computer vision community, to find new theoretical and experimental results. Finally, using the proposed framework, we evaluated a texture registration algorithm based on mutual information and found that its accuracy was under half-pixel.
Similar content being viewed by others
References
3D surface acquisition project. Website (2009). http://www.inf.uni-konstanz.de/cgip/projects/surfac
Bouguet, J.Y.: Camera calibration toolbox for Matlab. Website (2009). http://www.vision.caltech.edu/bouguetj/calib_doc
Clarkson, M.J., Rueckert, D., Hill, D.L.G., Hawkes, D.J.: Using photo-consistency to register 2D optical images of the human face to a 3D surface model. IEEE Trans. Pattern Anal. Mach. Intell. 23(11), 1266–1280 (2001)
Cleju, I.: Texture registration for 3D models. Ph.D. thesis, University of Konstanz (2008)
Cleju, I., Saupe, D.: Stochastic optimization of multiple texture registration using mutual information. In: LNCS Pattern Recognition: Proceedings Annual Symp. of the German Association for Pattern Recognition DAGM, vol. 4713, pp. 517–526. Springer, Berlin (2007)
Faugeras, O., Luong, Q.T.: The Geometry of Multiple Images. MIT, Cambridge (2001)
Hartley, R., Sturm, P.: Triangulation. Comput. Vis. Image Underst. 68(2), 146–157 (1997)
Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision, vol. 1. Cambridge University Press, Cambridge (2000)
Leedan, Y., Meer, P.: Heteroscedastic regression in computer vision: Problems with bilinear constraint. Int. J. Comput. Vis. 37(2), 127–150 (2000)
Lensch, H.P.A., Heidrich, W., Seidel, H.P.: A silhouette-based algorithm for texture registration and stitching. Graph. Models 63(4), 245–262 (2001)
Ma, Y., Koëcká, J., Sastry, S.: Optimization criteria and geometric algorithms for motion and structure estimation. Int. J. Comput. Vis. 44, 219–249 (2001)
Neugebauer, P.J., Klein, K.: Texturing 3D models of real world objects from multiple unregistered photographic views. Comput. Graph. Forum 3(18), 245–256 (1999)
Seitz, S., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: A comparison and evaluation of multi-view stereo reconstruction algorithms. In: Proceedings IEEE Conference Computer Vision Pattern Recognition, pp. 519–526. IEEE (2006)
Torr, P.H.S., Murray, D.W.: The development and comparison of robust methods for estimating the fundamental matrix. Int. J. Comput. Vis. 24(3), 271–300 (1997)
Troccoli, A.J., Allen, P.K.: Shadow based texture registration for 3D modeling of outdoor scenes. Mach. Vis. Appl. 18(2), 65–72 (2007)
Van de Kraats, E.B., Penney, G.P., Tomazevic, D., van Walsum, T., Niessen, W.J.: Standardized evaluation methodology for 2D–3D registration. IEEE Trans. Med. Imaging 24(9), 1177–1190 (2005)
Zhang, Z.: Determining the epipolar geometry and its uncertainty: A review. Int. J. Comput. Vis. 27, 161–195 (1998)
Zhang, Z.: On the optimization criteria used in two-view motion analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(7), 717–729 (1998)
Zhang, Z.: Flexible camera calibration by viewing a plane from unknown orientations. In: Proceedings International Conference on Computer Vision (ICCV’99), vol. 1, pp. 666–673. IEEE Computer Society (1999)
Author information
Authors and Affiliations
Corresponding author
Additional information
Work supported by the DFG Research Training Group 1042 Explorative Analysis and Visualization of Large Information Spaces at the University of Konstanz.
Rights and permissions
About this article
Cite this article
Cleju, I., Saupe, D. Evaluation of texture registration by epipolar geometry. Vis Comput 26, 1407–1420 (2010). https://doi.org/10.1007/s00371-010-0427-0
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-010-0427-0