ML Anthology

Bayesian Stereo Matching

Li Cheng, Terry Caelli
CVPR 2004 pp. 192
doi:10.1109/CVPR.2004.307 /cvpr/2004/cheng2004cvpr-bayesian/

Abstract

In this paper we explore a Bayesian framework for inferring the disparity map from an image pair. Markov Chain Monte Carlo sampling techniques are employed for learning the hyper-parameters which control two robust statistical functions for modelling the specific image pair; and loopy belief propagation is used for approximate inference of the MAP disparity map. Encouraging results are obtained on a standard set of image pairs.

CVPR Semantic Scholar

Cite

Text

Cheng and Caelli. "Bayesian Stereo Matching." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004. doi:10.1109/CVPR.2004.307

Markdown

[Cheng and Caelli. "Bayesian Stereo Matching." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2004.](https://mlanthology.org/cvpr/2004/cheng2004cvpr-bayesian/) doi:10.1109/CVPR.2004.307

BibTeX

@inproceedings{cheng2004cvpr-bayesian,
  title     = {{Bayesian Stereo Matching}},
  author    = {Cheng, Li and Caelli, Terry},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2004},
  pages     = {192},
  doi       = {10.1109/CVPR.2004.307},
  url       = {https://mlanthology.org/cvpr/2004/cheng2004cvpr-bayesian/}
}