Abstract
Energy-minimization methods are ubiquitous in computer vision and related fields. Low-level computer vision problems are typically defined on regular pixel lattices and seek to assign discrete or continuous values (or both) to each pixel such that a combined data term and a spatial smoothness prior are minimized. In this work we propose to minimize difficult energies using repeated generalized fusion moves. In contrast to standard fusion moves, the fusion step optimizes over binary and continuous sets of variables representing label ranges. Further, each fusion step can optimize over additional continuous unknowns. We demonstrate the general method on a variational-inspired stereo approach, and optionally optimize over radiometric changes between the images as well.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Zach, C., Kohli, P.: A convex discrete-continuous approach for Markov random fields. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 386–399. Springer, Heidelberg (2012). doi:10.1007/978-3-642-33783-3_28
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. 23, 1222–1239 (2001)
Gould, S., Amat, F., Koller, D.: Alphabet SOUP: a framework for approximate energy minimization. In: Proceedings of CVPR, pp. 903–910 (2009)
Carr, P., Hartley, R.: Solving multilabel graph cut problems with multilabel swap. In: 2009 Digital Image Computing: Techniques and Applications, DICTA 2009, pp. 532–539 (2009)
Schmidt, M., Alahari, K.: Generalized fast approximate energy minimization via graph cuts: alpha-expansion beta-shrink moves. In: Proceedings of UAI, pp. 653–660 (2011)
Veksler, O.: Graph cut based optimization for MRFs with truncated convex priors. In: Proceedings of CVPR (2007)
Kumar, M.P., Veksler, O., Torr, P.: Improved moves for truncated convex models. J. Mach. Learn. Res. 12, 31–67 (2011)
Veksler, O.: Multi-label moves for MRFs with truncated convex priors. Int. J. Comput. Vis. 98, 1–14 (2012)
Jezierska, A., Talbot, H., Veksler, O., Wesierski, D.: A fast solver for truncated-convex priors: quantized-convex split moves. In: Boykov, Y., Kahl, F., Lempitsky, V., Schmidt, F.R. (eds.) EMMCVPR 2011. LNCS, vol. 6819, pp. 45–58. Springer, Heidelberg (2011). doi:10.1007/978-3-642-23094-3_4
Woodford, O., Reid, I., Torr, P., Fitzgibbon, A.: Fields of experts for image-based rendering. In: Proceedings of BMVC (2006)
Lempitsky, V., Rother, C., Blake, A.: Logcut–efficient graph cut optimization for Markov random fields. In: Proceedings of ICCV (2007)
Lempitsky, V., Rother, C., Roth, S., Blake, A.: Fusion moves for Markov random field optimization. IEEE Trans. Pattern Anal. Mach. Intell. 32, 1392–1405 (2010)
Woodford, O., Torr, P., Reid, I., Fitzgibbon, A.: Global stereo reconstruction under second-order smoothness priors. IEEE Trans. Pattern Anal. Mach. Intell. 31, 2115–2128 (2009)
Ishikawa, H.: Higher-order gradient descent by fusion-move graph cut. In: Proceedings of ICCV (2009)
Trobin, W., Pock, T., Cremers, D., Bischof, H.: Continuous energy minimization via repeated binary fusion. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5305, pp. 677–690. Springer, Heidelberg (2008). doi:10.1007/978-3-540-88693-8_50
Olsson, C., Byrod, M., Overgaard, N., Kahl, F.: Extending continuous cuts: anisotropic metrics and expansion moves. In: Proceedings of CVPR, pp. 405–412 (2009)
Zach, C.: Dual decomposition for joint discrete-continuous optimization. In: Proceedings of AISTATS (2013)
Fix, A., Agarwal, S.: Duality and the continuous graphical model. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 266–281. Springer, Heidelberg (2014). doi:10.1007/978-3-319-10578-9_18
Möllenhoff, T., Laude, E., Moeller, M., Lellmann, J., Cremers, D.: Sublabel-accurate relaxation of nonconvex energies. In: Proceedings of CVPR (2016)
Dacorogna, B., Maréchal, P.: The role of perspective functions in convexity, polyconvexity, rank-one convexity and separate convexity. J. Convex Anal. 15, 271–284 (2008)
Kovtun, I.: Partial optimal labeling search for a NP-hard subclass of (max, +) problems. In: Michaelis, B., Krell, G. (eds.) DAGM 2003. LNCS, vol. 2781, pp. 402–409. Springer, Heidelberg (2003). doi:10.1007/978-3-540-45243-0_52
Kovtun, I.: Sufficient condition for partial optimality for (max, +) labeling problems and its usage. Technical report, International Research and Training Centre for Information Technologies and Systems (2010)
Shekhovtsov, A., Hlavac, V.: On partial optimality by auxiliary submodular problems. In: Control Systems and Computers, no. 2 (2011)
Desmet, J., Maeyer, M.D., Hazes, B., Lasters, I.: The dead-end elimination theorem and its use in protein side-chain positioning. Nature 356, 539–542 (1992)
Georgiev, I., Lilien, R.H., Donald, B.R.: The minimized dead-end elimination criterion and its application to protein redesign in a hybrid scoring and search algorithm for computing partition functions over molecular ensembles. J. Comput. Chem. 29, 1527–1542 (2008)
Gainza, P., Roberts, K.E., Donald, B.R.: Protein design using continuous rotamers. PLoS Comput. Biol. 8, e1002335 (2012)
Zach, C.: A principled approach for coarse-to-fine map inference. In: Proceedings of CVPR, pp. 1330–1337 (2014)
Pock, T., Chambolle, A.: Diagonal preconditioning for first order primal-dual algorithms in convex optimization. In: Proceedings of ICCV, pp. 1762–1769 (2011)
Seitz, S., Baker, S.: Filter flow. In: Proceedings of ICCV, pp. 143–150 (2009)
Hirschmüller, H., Scharstein, D.: Evaluation of stereo matching costs on images with radiometric differences. IEEE Trans. Pattern Anal. Mach. Intell. 31, 1582–1599 (2009)
Strecha, C., Tuytelaars, T., Van Gool, L.: Dense matching of multiple wide-baseline views. In: Proceedings of ICCV, pp. 1194–1201 (2003)
Sizintsev, M., Wildes, R.: Efficient stereo with accurate 3-D boundaries. Proc. BMVC 25(1–25), 10 (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Zach, C. (2017). Generalized Fusion Moves for Continuous Label Optimization. In: Lai, SH., Lepetit, V., Nishino, K., Sato, Y. (eds) Computer Vision – ACCV 2016. ACCV 2016. Lecture Notes in Computer Science(), vol 10115. Springer, Cham. https://doi.org/10.1007/978-3-319-54193-8_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-54193-8_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-54192-1
Online ISBN: 978-3-319-54193-8
eBook Packages: Computer ScienceComputer Science (R0)