Stereo Matching with Non-Linear Diffusion
Abstract
One of the central problems in stereo matching (and other image registration tasks) is the selection of optimal window sizes for comparing image regions. This paper addresses this problem with some novel algorithms based on iteratively diffusing support at different disparity hypotheses, and locally controlling the amount of diffusion based on the current quality of the disparity estimate. It also develops a novel Bayesian estimation technique which significantly outperforms techniques based on area-based matching (SSD) and regular diffusion. We provide experimental results on both synthetic and real stereo image pairs.
Cite
Text
Scharstein and Szeliski. "Stereo Matching with Non-Linear Diffusion." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996. doi:10.1109/CVPR.1996.517095Markdown
[Scharstein and Szeliski. "Stereo Matching with Non-Linear Diffusion." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1996.](https://mlanthology.org/cvpr/1996/scharstein1996cvpr-stereo-a/) doi:10.1109/CVPR.1996.517095BibTeX
@inproceedings{scharstein1996cvpr-stereo-a,
title = {{Stereo Matching with Non-Linear Diffusion}},
author = {Scharstein, Daniel and Szeliski, Richard},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {1996},
pages = {343-350},
doi = {10.1109/CVPR.1996.517095},
url = {https://mlanthology.org/cvpr/1996/scharstein1996cvpr-stereo-a/}
}