Abstract
This paper concerns the robust estimation of non-rigid deformations from feature correspondences. We advance the surprising view that for many realistic physical deformations, the error of the mismatches (outliers) usually dwarfs the effects of the curvature of the manifold on which the correct matches (inliers) lie, to the extent that one can tightly enclose the manifold within the error bounds of a low-dimensional hyperplane for accurate outlier rejection. This justifies a simple RANSAC-driven deformable registration technique that is at least as accurate as other methods based on the optimisation of fully deformable models. We support our ideas with comprehensive experiments on synthetic and real data typical of the deformations examined in the literature.
Chapter PDF
Similar content being viewed by others
Keywords
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.
References
Pilet, J., Lepetit, V., Fua, P.: Real-time non-rigid surface detection. In: CVPR (2005)
Pilet, J., Lepetit, V., Fua, P.: Fast non-rigid surface detection, registration and realistic augmentation. IJCV 76, 109–122 (2008)
Zhu, J., Lyu, M.R.: Progressive finite newton approach to real-time nonrigid surface detection. In: CVPR (2007)
Zhu, J., Hoi, C.H., Lyu, M.R.: Nonrigid shape recovery by gaussian process registration. In: CVPR (2009)
Bookstein, F.L.: Principal warps: thin-plate splines and the decomposition of deformations. IEEE TPAMI 11, 567–585 (1989)
Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24 (1981)
Carneiro, G., Jepson, A.D.: Flexible spatial configuration of local image features. IEEE TPAMI 29, 2089–2104 (2007)
Bartoli, A.: Maximizing the predictivity of smooth deformable image warps through cross-validation. J. Math. Imaging Vis. 31, 233–244 (2008)
Pizarro, D., Bartoli, A.: Feature-based deformable surface detection with self-occlusion reasoning. IJCV (to appear)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)
Li, X., Hu, Z.: Rejecting mismatches by correspondence function. IJCV 89, 1–17 (2010)
Chum, O., Matas, J.: Matching with prosac - progressive sample consensus. In: CVPR (2005)
Li, X., Li, X., Li, H., Cao, M.: Rejecting outliers based on correspondence manifold. Acta Automatica Sinica 35, 17–22 (2009)
Bartoli, A., Zisserman, A.: Direct estimation of non-rigid registrations. In: BMVC (2004)
Gay-Bellile, V., Bartoli, A., Sayd, P.: Direct estimation of nonrigid registrations with image-based self-occlusion reasoning. IEEE TPAMI 32, 87–104 (2010)
Varol, A., Salzmann, M., Tola, E., Fua, P.: Template-free monocular reconstruction of deformable surfaces. In: ICCV (2009)
Taylor, J., Jepson, A., Kutulakos, K.: Non-rigid structure from locally rigid motion. In: CVPR (2010)
Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE TPAMI 24, 509–521 (2002)
Chui, H., Rangarajan, A.: A new point matching algorithm for non-rigid registration. CVIU 89, 114–141 (2003)
Choi, S., Kim, T., Yu, W.: Performance evaluation of RANSAC family. In: BMVC (2009)
Chen, H., Meer, P.: Robust regression with projection based m-estimators. In: ICCV (2003)
Rozenfeld, S., Shimshoni, I.: The modified pbm-estimator method and a runtime analysis technique for the ransac family. In: CVPR (2005)
Donato, G., Belongie, S.: Approximate Thin Plate Spline Mappings. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part III. LNCS, vol. 2352, pp. 21–31. Springer, Heidelberg (2002)
Salzmann, M., Fua, P.: Reconstructing sharply folding surfaces: a convex formulation. In: CVPR (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tran, QH., Chin, TJ., Carneiro, G., Brown, M.S., Suter, D. (2012). In Defence of RANSAC for Outlier Rejection in Deformable Registration. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7575. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33765-9_20
Download citation
DOI: https://doi.org/10.1007/978-3-642-33765-9_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33764-2
Online ISBN: 978-3-642-33765-9
eBook Packages: Computer ScienceComputer Science (R0)