Abstract
As richer models for stereo vision are constructed, there is a growing interest in learning model parameters. To estimate parameters in Markov Random Field (MRF) based stereo formulations, one usually needs to perform approximate probabilistic inference. Message passing algorithms based on variational methods and belief propagation are widely used for approximate inference in MRFs. Conditional Random Fields (CRFs) are discriminative versions of traditional MRFs and have recently been applied to the problem of stereo vision. However, CRF parameter training typically requires expensive inference steps for each iteration of optimization. Inference is particularly slow when there are many discrete disparity levels, due to high state space cardinality. We present a novel CRF for stereo matching with an explicit occlusion model and propose sparse message passing to dramatically accelerate the approximate inference needed for parameter optimization. We show that sparse variational message passing iteratively minimizes the KL divergence between the approximation and model distributions by optimizing a lower bound on the partition function. Our experimental results show reductions in inference time of one order of magnitude with no loss in approximation quality. Learning using sparse variational message passing improves results over prior work using graph cuts.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Kolmogorov, V., Zabih, R.: Computing visual correspondence with occlusions using graph cuts. In: Proc. ICCV, pp. 508–515 (2001)
Sun, J., Li, Y., Kang, S.B., Shum, H.Y.: Symmetric stereo matching for occlusion handling. In: Proc. CVPR, pp. 399–406 (2005)
Yang, Q., Wang, L., Yang, R., Stewenius, H., Nister, D.: Stereo matching with color-weighted correlation, hierachical belief propagation and occlusion handling. In: Proc. CVPR (2006)
Yedidia, J., Freeman, W., Weiss, Y.: Understanding belief propagation and its generalizations. In: Exploring Artificial Intelligence in the New Millennium, pp. 236–239 (January 2003)
Jordan, M.I., Ghahramani, Z., Jaakkola, T., Saul, L.: Introduction to variational methods for graphical models. Machine Learning 37, 183–233 (1999)
Blei, D., Ng, A., Jordan, M.: Latent Dirichlet allocation. J. of Machine Learning Research 3, 993–1022 (2003)
Frey, B.J., Jojic, N.: A comparison of algorithms for inference and learning in probabilistic graphical models. IEEE TPAMI 27(9) (September 2005)
Winn, J., Bishop, C.: Variational message passing. J. of Machine Learning Research 6, 661–694 (2005)
Andrieu, C., de Freitas, N., Doucet, A., Jordan, M.: An introduction to MCMC for machine learning. Machine Learning 50, 5–43 (2003)
Pal, C., Sutton, C., McCallum, A.: Sparse forward-backward using minimum divergence beams for fast training of conditional random fields. In: Proc. ICASSP, pp. 581–584 (2006)
Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Proc. ICML, pp. 282–289 (2001)
Kumar, S., Hebert, M.: Discriminative random fields. IJCV 68(2), 179–201 (2006)
Weinman, J., Hanson, A., McCallum, A.: Sign detection in natural images with conditional random fields. In: IEEE Intl. Workshop on Machine Learning for Signal Processing, pp. 549–558 (2004)
He, Z., Zemel, R.S., Carreira-Perpin, M.: Multiscale conditional random fields for image labeling. In: Proc. CVPR, pp. 695–702 (2004)
Scharstein, D., Pal, C.: Learning conditional random fields for stereo. In: Proc. CVPR (2007)
Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. IEEE TPAMI 28, 1568–1583 (2006)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. IEEE TPAMI 23(11), 1222–1239 (2001)
Birchfield, S., Tomasi, C.: A pixel dissimilarity measure that is insensitive to image sampling. IEEE TPAMI 20(4), 401–406 (1998)
Weinman, J., Pal, C., Scharstein, D.: Sparse message passing and efficiently learning random fields for stereo vision. Technical Report UM-CS-2007-054, U. Massachusetts Amherst (October 2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Weinman, J.J., Tran, L., Pal, C.J. (2008). Efficiently Learning Random Fields for Stereo Vision with Sparse Message Passing. In: Forsyth, D., Torr, P., Zisserman, A. (eds) Computer Vision – ECCV 2008. ECCV 2008. Lecture Notes in Computer Science, vol 5302. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-88682-2_47
Download citation
DOI: https://doi.org/10.1007/978-3-540-88682-2_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-88681-5
Online ISBN: 978-3-540-88682-2
eBook Packages: Computer ScienceComputer Science (R0)