Abstract
Optimization with graph cuts became very popular in recent years. As more applications rely on graph cuts, different energy functions are being employed. Recent evaluation of optimization algorithms showed that the widely used swap and expansion graph cut algorithms have an excellent performance for energies where the underlying MRF has Potts prior. Potts prior corresponds to assuming that the true labeling is piecewise constant. While surprisingly useful in practice, Potts prior is clearly not appropriate in many circumstances. However for more general priors, the swap and expansion algorithms do not perform as well. Both algorithms are based on moves that give each pixel a choice of only two labels. Therefore such moves can be referred to as binary moves. Recently, range moves that act on multiple labels simultaneously were introduced. As opposed to swap and expansion, each pixel has a choice of more than two labels in a range move. Therefore we call them multi-label moves. Range moves were shown to work better for problems with truncated convex priors, which imply a piecewise smooth labeling. Inspired by range moves, we develop several different variants of multi-label moves. We evaluate them on the problem of stereo correspondence and discuss their relative merits.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Ishikawa, H., Geiger, D.: Occlusions, discontinuities, and epipolar lines in stereo. In: Burkhardt, H.-J., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1406, p. 232. Springer, Heidelberg (1998)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. PAMI 23(11), 1222–1239 (2001)
Kolmogorov, V., Zabih, R.: What energy functions can be minimized via graph cuts? In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 65–81. Springer, Heidelberg (2002)
Boykov, Y., Veksler, O., Zabih, R.: Markov random fields with efficient approximations. In: CVPR, pp. 648–655 (1998)
Kolmogorov, V., Zabih, R.: Computing visual correspondence with occlusions via graph cuts. In: ICCV, vol. II, pp. 508–515 (2001)
Kolmogorov, V., Zabih, R.: Multi-camera scene reconstruction via graph cuts. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 82–96. Springer, Heidelberg (2002)
Lempitsky, V., Boykov, Y., Ivanov, D.: Oriented visibility for multiview reconstruction. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3953, pp. 226–238. Springer, Heidelberg (2006)
Wills, J., Agarwal, S., Belongie, S.: What went where. In: CVPR, vol. I, pp. 37–44 (2003)
Xiao, J., Shah, M.: Motion layer extraction in the presence of occlusion using graph cuts. PAMI 27(10), 1644–1659 (2005)
Schoenemann, T., Cremers, D.: High resolution motion layer decomposition using dual-space graph cuts. In: CVPR, pp. 1–7 (2008)
Kwatra, V., Schödl, A., Essa, I., Turk, G., Bobick, A.: Graphcut textures: Image and video synthesis using graph cuts. ACM Transactions on Graphics, SIGGRAPH 2003 22(3), 277–286 (2003)
Boykov, Y., Jolly, M.: Interactive graph cuts for optimal boundary and region segmentation of objects in n-d images. In: ICCV, vol. I, pp. 105–112 (2001)
Blake, A., Rother, C., Brown, M., Perez, P., Torr, P.: Interactive image segmentation using an adaptive GMMRF model. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 428–441. Springer, Heidelberg (2004)
Rother, C., Minka, T., Blake, A., Kolmogorov, V.: Cosegmentation of image pairs by histogram matching: Incorporating a global constraint into mrfs. In: CVPR, vol. I, pp. 993–1000 (2006)
Kolmogorov, V., Criminisi, A., Blake, A., Cross, G., Rother, C.: Probabilistic fusion of stereo with color and contrast for bilayer segmentation. PAMI 28(9), 1480–1492 (2006)
Agarwala, A., Dontcheva, M., Agrawala, M., Drucker, S., Colburn, A., Curless, B., Salesin, D., Cohen, M.: Iteractive digital photomontage. In: ACM Transactions on Graphics, SIGGRAPH (2004)
Ishikawa, H.: Exact optimization for markov random fields with convex priors. PAMI 25(10), 1333–1336 (2003)
Szeliski, R., Zabih, R., Scharstein, D., Veksler, O., Kolmogorov, V., Agarwala, A., Tappen, M., Rother, C.: A comparative study of energy minimization methods for markov random fields with smoothness-based priors. IEEE Transacions on Pattern Analysis and Machine Intellegence 30(6), 1068–1080 (2008)
Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. PAMI 28(10), 1568–1583 (2006)
Pearl, J.: Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann, San Francisco (1988)
Kolmogorov, V., Rother, C.: Comparison of energy minimization algorithms for highly connected graphs. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 1–15. Springer, Heidelberg (2006)
Veksler, O.: Graph cut based optimization for mrfs with truncated convex priors. In: CVPR, pp. 1–8 (2007)
Liu, X., Veksler, O., Samarabandu, J.: Graph cut with ordering constraints on labels and its applications. In: CVPR, pp. 1–8 (2008)
Kumar, M.P., Torr, P.H.S.: Improved moves for truncated convex models. In: Koller, D., Schuurmans, D., Bengio, Y., Bottou, L. (eds.) Advances in Neural Information Processing Systems 21, pp. 889–896 (2009)
Torr, P.H.S.: In: Personal communication (2008)
Hunter, D.R., Lange, K.: A tutorial on MM algorithms. The American Statistician (58) (2004)
Schlesinger, D., Flach, B.: Transforming an arbitrary minsum problem into a binary one. Technical Report TUD-FI06-01, Dresden University of Technology (2006)
Darbon, J.: Global optimization for first order markov random fields with submodular priors. In: Brimkov, V.E., Barneva, R.P., Hauptman, H.A. (eds.) IWCIA 2008. LNCS, vol. 4958, pp. 229–237. Springer, Heidelberg (2008)
Kolmogorov, V.: Primal-dual algorithm for convex markov random fields. Technical Report MSR-TR-2005-117, Microsoft (2005)
Rother, C., Kumar, S., Kolmogorov, V., Blake, A.: Digital tapestry. In: CVPR, vol. I, pp. 589–596 (2005)
Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. IJCV 47(1-3), 7–42 (2002)
Scharstein, D., Szeliski, R.: High-accuracy stereo depth maps using structured light. In: CVPR, vol. I, pp. 195–202 (2003)
Alahari, K., Kohli, P., Torr, P.: Reduce, reuse, recycle: Efficiently solving multi-label mrfs. In: CVPR, pp. 1–8 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Veksler, O. (2009). Multi-label Moves for MRFs with Truncated Convex Priors. In: Cremers, D., Boykov, Y., Blake, A., Schmidt, F.R. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 2009. Lecture Notes in Computer Science, vol 5681. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03641-5_1
Download citation
DOI: https://doi.org/10.1007/978-3-642-03641-5_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03640-8
Online ISBN: 978-3-642-03641-5
eBook Packages: Computer ScienceComputer Science (R0)