Abstract
Second derivative regularization methods for dense stereo matching is a topic of intense research. Some of the most successful recent methods employ so called binary fusion moves where the combination of two proposal solutions is computed. In many cases the fusion move can be solved optimally, but the approach is limited to fusing pairs of proposals in each move. For multiple proposals iterative binary fusion may potentially lead to local minima.
In this paper we demonstrate how to simultaneously fuse more than two proposals at the same time for a 2nd order stereo regularizer. The optimization is made possible by effectively computing a generalized distance transform. This allows for computation of messages in linear time in the number of proposals. In addition the approach provides a lower bound on the globally optimal solution of the multi-fusion problem. We verify experimentally that the lower bound is very close to the computed solution, thus providing a near optimal solution.
This work has been funded by the Swedish Research Council (grant 2012-4213), the Swedish Foundation for Strategic Research (SSF) through the program Future Research Leaders, the ELLIIT program and by the European Research Council (GlobalVision grant no. 209480).
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 subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Birchfield, S., Tomasi, C.: Multiway cut for stereo and motion with slanted surfaces. In: Int. Conf. Computer Vision (1999)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Analysis and Machine Intelligence (2001)
Felzenszwalb, P., Huttenlocher, D.: Efficient belief propagation for early vision. In: Int. Conf. Computer Vision, vol. 70(1), pp. 41–54 (2006)
Hirschmüller, H., Scharstein, D.: Evaluation of cost functions for stereo matching. In: Conf. Computer Vision and Pattern Recognition (2007)
Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. IEEE Trans. Pattern Analysis and Machine Intelligence 28(10), 1568–1583 (2006)
Kolmogorov, V., Zabih, R.: Multi-camera scene reconstruction via graph cuts. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002, Part III. LNCS, vol. 2352, pp. 82–96. Springer, Heidelberg (2002)
Komodakis, N., Paragios, N., Tziritas, G.: Mrf optimization via dual decomposition: Message-passing revisited. In: Int. Conf. Computer Vision. IEEE (2007)
Lempitsky, V.S., Rother, C., Roth, S., Blake, A.: Fusion moves for markov random field optimization. IEEE Trans. Pattern Analysis and Machine Intelligence 32(8), 1392–1405 (2010)
Li, G., Zucker, S.: Differential geometric inference in surface stereo. IEEE Trans. Pattern Analysis and Machine Intelligence 32(1), 72–86 (2010)
Olsson, C., Ulén, J., Boykov, Y.: In Defense of 3D-Label Stereo. In: Conf. Computer Vision and Pattern Recognition (2013)
Rother, C., Kolmogorov, V., Lempitsky, V., Szummer, M.: Optimizing binary mrfs via extended roof duality. In: Conf. Computer Vision and Pattern Recognition (2007)
Scharstein, D., Pal, C.: Learning conditional random fields for stereo. In: Conf. Computer Vision and Pattern Recognition (2007)
Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. Journal Computer Vision 47(1), 7–42 (2002)
Scharstein, D., Szeliski, R.: High-accuracy stereo depth maps using structured light. In: Conf. Computer Vision and Pattern Recognition (2003)
Veksler, O.: Multi-label moves for MRFs with truncated convex priors. In: Cremers, D., Boykov, Y., Blake, A., Schmidt, F.R. (eds.) EMMCVPR 2009. LNCS, vol. 5681, pp. 1–13. Springer, Heidelberg (2009)
Wainwright, M., Jaakkola, T., Willsky, A.: Map estimation via agreement on trees: message-passing and linear programming. IEEE Trans. Information Theory (2005)
Woodford, O., Torr, P., Reid, I., Fitzgibbon, A.: Global stereo reconstruction under second-order smoothness priors. IEEE Trans. Pattern Analysis and Machine Intelligence 31(12), 2115–2128 (2009)
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ulén, J., Olsson, C. (2013). Simultaneous Fusion Moves for 3D-Label Stereo. In: Heyden, A., Kahl, F., Olsson, C., Oskarsson, M., Tai, XC. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 2013. Lecture Notes in Computer Science, vol 8081. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40395-8_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-40395-8_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40394-1
Online ISBN: 978-3-642-40395-8
eBook Packages: Computer ScienceComputer Science (R0)