Parameter estimation for MRF stereo

• Published in: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) Vol. 2; pp. 288 - 295 vol. 2
• Main Authors: Zhang, L., Seitz, S.M.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 2005
• Subjects: Belief propagation; Computer vision; Energy measurement; Iterative algorithms; Joining processes; Markov random fields; Parameter estimation; Pixel; Robustness; Stereo vision
• ISBN: 0769523722; 9780769523729
• ISSN: 1063-6919; 1063-6919
• DOI: 10.1109/CVPR.2005.269

This paper presents a novel approach for estimating parameters for MRF-based stereo algorithms. This approach is based on a new formulation of stereo as a maximum a posterior (MAP) problem, in which both a disparity map and MRF parameters are estimated from the stereo pair itself. We present an iterative algorithm for the MAP estimation that alternates between estimating the parameters while fixing the disparity map and estimating the disparity map while fixing the parameters. The estimated parameters include robust truncation thresholds, for both data and neighborhood terms, as well as a regularization weight. The regularization weight can be either a constant for the whole image, or spatially-varying, depending on local intensity gradients. In the latter case, the weights for intensity gradients are also estimated. Experiments indicate that our approach, as a wrapper for existing stereo algorithms, moves a baseline belief propagation stereo algorithm up six slots in the middlebury rankings.