Abstract
Geometric estimation from image point correspondences is the core procedure of many 3D vision problems, which is prevalently accomplished by random sampling techniques. In this paper, we consider the problem from an optimization perspective, to exploit the intrinsic linear structure of point correspondences to assist estimation. We generalize the conventional method to a robust one and extend the previous analysis for linear structure to develop several new algorithms. The proposed solutions essentially address the estimation problem by solving a subspace recovery problem to identify the inliers. Experiments on real-world image datasets for both fundamental matrix and homography estimation demonstrate the superiority of our method over the state-of-the-art in terms of both robustness and accuracy.
J. Ma—This work was supported by the National Natural Science Foundation of China under Grant nos. 61773295 and 61971165.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Barath, D., Matas, J.: Graph-cut RANSAC. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6733–6741 (2018)
Barath, D., Matas, J., Noskova, J.: MAGSAC: marginalizing sample consensus. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10197–10205 (2019)
Bazin, J.C., Li, H., Kweon, I.S., Demonceaux, C., Vasseur, P., Ikeuchi, K.: A branch-and-bound approach to correspondence and grouping problems. IEEE Trans. Pattern Anal. Mach. Intell. 35(7), 1565–1576 (2012)
Bazin, J.-C., Seo, Y., Hartley, R., Pollefeys, M.: Globally optimal inlier set maximization with unknown rotation and focal length. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 803–817. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10605-2_52
Brown, M., Lowe, D.G.: Automatic panoramic image stitching using invariant features. Int. J. Comput. Vis. 74(1), 59–73 (2007)
Cai, Z., Chin, T.J., Koltun, V.: Consensus maximization tree search revisited. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1637–1645 (2019)
Cai, Z., Chin, T.J., Le, H., Suter, D.: Deterministic consensus maximization with biconvex programming. In: Proceedings of the European Conference on Computer Vision, pp. 685–700 (2018)
Campbell, D., Petersson, L., Kneip, L., Li, H.: Globally-optimal inlier set maximisation for simultaneous camera pose and feature correspondence. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1–10 (2017)
Chum, O., Matas, J.: Matching with PROSAC-progressive sample consensus. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 220–226 (2005)
Chum, O., Matas, J.: Optimal randomized RANSAC. IEEE Trans. Pattern Anal. Mach. Intell. 30(8), 1472–1482 (2008)
Chum, O., Matas, J., Kittler, J.: Locally optimized RANSAC. In: Michaelis, B., Krell, G. (eds.) DAGM 2003. LNCS, vol. 2781, pp. 236–243. Springer, Heidelberg (2003). https://doi.org/10.1007/978-3-540-45243-0_31
Chum, O., Werner, T., Matas, J.: Two-view geometry estimation unaffected by a dominant plane. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 772–779 (2005)
Ding, T., et al.: Noisy dual principal component pursuit. In: Proceedings of the International Conference on Machine Learning, pp. 1617–1625 (2019)
Enqvist, O., Ask, E., Kahl, F., Åström, K.: Tractable algorithms for robust model estimation. Int. J. Comput. Vis. 112(1), 115–129 (2015)
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(6), 381–395 (1981)
Fragoso, V., Sen, P., Rodriguez, S., Turk, M.: EVSAC: accelerating hypotheses generation by modeling matching scores with extreme value theory. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2472–2479 (2013)
Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2003)
Le, H.M., Chin, T.J., Eriksson, A., Do, T.T., Suter, D.: Deterministic approximate methods for maximum consensus robust fitting. IEEE Trans. Pattern Anal. Mach. Intell. (2019)
Lebeda, K., Matas, J., Chum, O.: Fixing the locally optimized RANSAC-full experimental evaluation. In: Proceedings of the British Machine Vision Conference, pp. 1–11 (2012)
Lerman, G., Maunu, T.: An overview of robust subspace recovery. Proc. IEEE 106(8), 1380–1410 (2018)
Lerman, G., McCoy, M.B., Tropp, J.A., Zhang, T.: Robust computation of linear models by convex relaxation. Found. Comput. Math. 15(2), 363–410 (2015)
Li, H.: Consensus set maximization with guaranteed global optimality for robust geometry estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1074–1080 (2009)
Ma, J., Zhao, J., Jiang, J., Zhou, H., Guo, X.: Locality preserving matching. Int. J. Comput. Vis. 127(5), 512–531 (2019)
Ma, J., Zhao, J., Tian, J., Yuille, A.L., Tu, Z.: Robust point matching via vector field consensus. IEEE Trans. Image Process. 23(4), 1706–1721 (2014)
Matas, J., Chum, O.: Randomized RANSAC with Td, d test. Image Vis. Comput. 22(10), 837–842 (2004)
Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: ORB-SLAM: a versatile and accurate monocular slam system. IEEE Trans. Rob. 31(5), 1147–1163 (2015)
Ni, K., Jin, H., Dellaert, F.: GroupSAC: efficient consensus in the presence of groupings. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2193–2200 (2009)
Purkait, P., Zach, C., Eriksson, A.: Maximum consensus parameter estimation by reweighted \(\ell _1\) methods. In: Pelillo, M., Hancock, E. (eds.) EMMCVPR 2017. LNCS, vol. 10746, pp. 312–327. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-78199-0_21
Raguram, R., Chum, O., Pollefeys, M., Matas, J., Frahm, J.M.: USAC: a universal framework for random sample consensus. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 2022–2038 (2012)
Torr, P.H.S.: Bayesian model estimation and selection for epipolar geometry and generic manifold fitting. Int. J. Comput. Vis. 50(1), 35–61 (2002)
Torr, P.H., Nasuto, S.J., Bishop, J.M.: NAPSAC: high noise, high dimensional robust estimation-it’s in the bag. In: British Machine Vision Conference (BMVC) (2002)
Torr, P.H., Zisserman, A.: MLESAC: a new robust estimator with application to estimating image geometry. Comput. Vis. Image Underst. 78(1), 138–156 (2000)
Tsakiris, M.C., Vidal, R.: Dual principal component pursuit. J. Mach. Learn. Res. 19(1), 684–732 (2018)
Vincent, E., Laganiére, R.: Detecting planar homographies in an image pair. In: Proceedings of the International Symposium on Image and Signal Processing and Analysis, pp. 182–187 (2001)
Zhu, Z., Wang, Y., Robinson, D., Naiman, D., Vidal, R., Tsakiris, M.: Dual principal component pursuit: improved analysis and efficient algorithms. In: Advances in Neural Information Processing Systems, pp. 2171–2181 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Fan, A., Jiang, X., Wang, Y., Jiang, J., Ma, J. (2020). Geometric Estimation via Robust Subspace Recovery. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12367. Springer, Cham. https://doi.org/10.1007/978-3-030-58542-6_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-58542-6_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58541-9
Online ISBN: 978-3-030-58542-6
eBook Packages: Computer ScienceComputer Science (R0)