MAP Disparity Estimation Using Hidden Markov Trees
Abstract
A new method is introduced for stereo matching that operates on minimum spanning trees (MSTs) generated from the images. Disparity maps are represented as a collection of hidden states on MSTs, and each MST is modeled as a hidden Markov tree. An efficient recursive message-passing scheme designed to operate on hidden Markov trees, known as the upward-downward algorithm, is used to compute the maximum a posteriori (MAP) disparity estimate at each pixel. The messages processed by the upward-downward algorithm involve two types of probabilities: the probability of a pixel having a particular disparity given a set of per-pixel matching costs, and the probability of a disparity transition between a pair of connected pixels given their similarity. The distributions of these probabilities are modeled from a collection of images with ground truth disparities. Performance evaluation using the Middlebury stereo benchmark version 3 demonstrates that the proposed method ranks second and third in terms of overall accuracy when evaluated on the training and test image sets, respectively.
Cite
Text
Psota et al. "MAP Disparity Estimation Using Hidden Markov Trees." International Conference on Computer Vision, 2015. doi:10.1109/ICCV.2015.256Markdown
[Psota et al. "MAP Disparity Estimation Using Hidden Markov Trees." International Conference on Computer Vision, 2015.](https://mlanthology.org/iccv/2015/psota2015iccv-map/) doi:10.1109/ICCV.2015.256BibTeX
@inproceedings{psota2015iccv-map,
title = {{MAP Disparity Estimation Using Hidden Markov Trees}},
author = {Psota, Eric T. and Kowalczuk, Jedrzej and Mittek, Mateusz and Perez, Lance C.},
booktitle = {International Conference on Computer Vision},
year = {2015},
doi = {10.1109/ICCV.2015.256},
url = {https://mlanthology.org/iccv/2015/psota2015iccv-map/}
}