International Journal of Computer Vision

, Volume 99, Issue 3, pp 319–337

On Learning Conditional Random Fields for Stereo

Exploring Model Structures and Approximate Inference
  • Christopher J. Pal
  • Jerod J. Weinman
  • Lam C. Tran
  • Daniel Scharstein

DOI: 10.1007/s11263-010-0385-z

Cite this article as:
Pal, C.J., Weinman, J.J., Tran, L.C. et al. Int J Comput Vis (2012) 99: 319. doi:10.1007/s11263-010-0385-z


Until recently, the lack of ground truth data has hindered the application of discriminative structured prediction techniques to the stereo problem. In this paper we use ground truth data sets that we have recently constructed to explore different model structures and parameter learning techniques. To estimate parameters in Markov random fields (MRFs) via maximum likelihood one usually needs to perform approximate probabilistic inference. Conditional random fields (CRFs) are discriminative versions of traditional MRFs. We explore a number of novel CRF model structures including a CRF for stereo matching with an explicit occlusion model. CRFs require expensive inference steps for each iteration of optimization and inference is particularly slow when there are many discrete states. We explore belief propagation, variational message passing and graph cuts as inference methods during learning and compare with learning via pseudolikelihood. To accelerate approximate inference we have developed a new method called sparse variational message passing which can reduce inference time by an order of magnitude with negligible loss in quality. Learning using sparse variational message passing improves upon previous approaches using graph cuts and allows efficient learning over large data sets when energy functions violate the constraints imposed by graph cuts.


Stereo Learning Structured prediction Approximate inference 

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  • Christopher J. Pal
    • 1
  • Jerod J. Weinman
    • 2
  • Lam C. Tran
    • 3
  • Daniel Scharstein
    • 4
  1. 1.École Polytechnique de MontréalMontréalCanada
  2. 2.Dept. of Computer ScienceGrinnell CollegeGrinnellUSA
  3. 3.Dept. of Electrical and Computer EngineeringUniversity of California San DiegoSan DiegoUSA
  4. 4.Middlebury CollegeMiddleburyUSA

Personalised recommendations