Accurate stereo matching by two-step energy minimization

Mikhail G. Mozerov, Joost Van De Weijer

    Research output: Contribution to journalArticleResearchpeer-review

    106 Citations (Scopus)

    Abstract

    © 2014 IEEE. In stereo matching, cost-filtering methods and energy-minimization algorithms are considered as two different techniques. Due to their global extent, energy-minimization methods obtain good stereo matching results. However, they tend to fail in occluded regions, in which cost-filtering approaches obtain better results. In this paper, we intend to combine both the approaches with the aim to improve overall stereo matching results. We show that a global optimization with a fully connected model can be solved by cost-filtering methods. Based on this observation, we propose to perform stereo matching as a two-step energy-minimization algorithm. We consider two Markov random field (MRF) models: 1) a fully connected model defined on the complete set of pixels in an image and 2) a conventional locally connected model. We solve the energy-minimization problem for the fully connected model, after which the marginal function of the solution is used as the unary potential in the locally connected MRF model. Experiments on the Middlebury stereo data sets show that the proposed method achieves the state-of-the-arts results.
    Original languageEnglish
    Article number7018068
    Pages (from-to)1153-1163
    JournalIEEE Transactions on Image Processing
    Volume24
    Issue number3
    DOIs
    Publication statusPublished - 1 Mar 2015

    Keywords

    • bilateral filter
    • energy minimization
    • fully connected MRF model
    • Stereo matching

    Fingerprint Dive into the research topics of 'Accurate stereo matching by two-step energy minimization'. Together they form a unique fingerprint.

    Cite this