Robust Global Translations with 1DSfM
Conference paper
Abstract
We present a simple, effective method for solving structure from motion problems by averaging epipolar geometries. Based on recent successes in solving for global camera rotations using averaging schemes, we focus on the problem of solving for 3D camera translations given a network of noisy pairwise camera translation directions (or 3D point observations). To do this well, we have two main insights. First, we propose a method for removing outliers from problem instances by solving simpler low-dimensional subproblems, which we refer to as 1DSfM problems. Second, we present a simple, principled averaging scheme. We demonstrate this new method in the wild on Internet photo collections.
Keywords
Structure from Motion translations problem robust estimation Download
to read the full conference paper text
References
- 1.Agarwal, S., Mierle, K., et al.: Ceres solver, https://code.google.com/p/ceres-solver/
- 2.Agarwal, S., Snavely, N., Simon, I., Seitz, S.M., Szeliski, R.: Building Rome in a day. In: ICCV (2009)Google Scholar
- 3.Arie-Nachimson, M., Shahar, S.Z., Kemelmacher-Shlizerman, I., Singer, A., Basri, R.: Global motion estimation from point matches. In: 3DIMPVT (2012)Google Scholar
- 4.Brand, M., Antone, M., Teller, S.: Spectral solution of large-scale extrinsic camera calibration as a graph embedding problem. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3022, pp. 262–273. Springer, Heidelberg (2004)CrossRefGoogle Scholar
- 5.Chatterjee, A., Govindu, V.M.: Efficient and robust large-scale rotation averaging. In: ICCV (2013)Google Scholar
- 6.Crandall, D., Owens, A., Snavely, N., Huttenlocher, D.: Discrete-continuous optimization for large-scale structure from motion. In: CVPR (2011)Google Scholar
- 7.Eades, P., Lin, X., Smyth, W.F.: A fast and effective heuristic for the feedback arc set problem. In: Information Processing Letters (1993)Google Scholar
- 8.Enqvist, O., Kahl, F., Olsson, C.: Nonsequential structure from motion. In: OMNIVIS (2011)Google Scholar
- 9.Frahm, J.-M., et al.: Building Rome on a cloudless day. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 368–381. Springer, Heidelberg (2010)CrossRefGoogle Scholar
- 10.Fredriksson, J., Olsson, C.: Simultaneous multiple rotation averaging using Lagrangian duality. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012, Part III. LNCS, vol. 7726, pp. 245–258. Springer, Heidelberg (2013)CrossRefGoogle Scholar
- 11.Govindu, V.M.: Combining two-view constraints for motion estimation. In: CVPR (2001)Google Scholar
- 12.Govindu, V.M.: Lie-algebraic averaging for globally consistent motion estimation. In: CVPR (2004)Google Scholar
- 13.Hartley, R., Aftab, K., Trumpf, J.: L 1 rotation averaging using the Weiszfeld algorithm. In: CVPR (2011)Google Scholar
- 14.Jiang, N., Cui, Z., Tan, P.: A global linear method for camera pose registration. In: ICCV (2013)Google Scholar
- 15.Jiang, N., Tan, P., Cheong, L.: Seeing double without confusion: Structure-from-motion in highly ambiguous scenes. In: CVPR (2012)Google Scholar
- 16.Kahl, F.: Multiple view geometry and the L ∞ -norm. In: ICCV (2005)Google Scholar
- 17.Martinec, D., Pajdla, T.: Robust rotation and translation estimation in multiview reconstruction. In: CVPR (2007)Google Scholar
- 18.Sinha, S.N., Steedly, D., Szeliski, R.: A multi-stage linear approach to structure from motion. In: Kutulakos, K.N. (ed.) ECCV 2010 Workshops, Part II. LNCS, vol. 6554, pp. 267–281. Springer, Heidelberg (2012)CrossRefGoogle Scholar
- 19.Snavely, N., Seitz, S., Szeliski, R.: Photo tourism: Exploring photo collections in 3D. In: SIGGRAPH (2006)Google Scholar
- 20.Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: A factorization method. In: IJCV (1992)Google Scholar
- 21.Triggs, B., McLauchlan, P.F., Hartley, R.I., Fitzgibbon, A.W.: Bundle adjustment—a modern synthesis. In: Triggs, B., Zisserman, A., Szeliski, R. (eds.) Vision Algorithms 1999. LNCS, vol. 1883, pp. 298–372. Springer, Heidelberg (2000)Google Scholar
- 22.Wilson, K., Snavely, N.: Network principles for SfM: Disambiguating repeated structures with local context. In: ICCV (2013)Google Scholar
- 23.Zach, C., Klopschitz, M., Pollefeys, M.: Disambiguating visual relationships using loop constraints. In: CVPR (2010)Google Scholar
Copyright information
© Springer International Publishing Switzerland 2014