NB-GTR: Narrow-Band Guided Turbulence Removal
Abstract
The removal of atmospheric turbulence is crucial for long-distance imaging. Leveraging the stochastic nature of atmospheric turbulence numerous algorithms have been developed that employ multi-frame input to mitigate the turbulence. However when limited to a single frame existing algorithms face substantial performance drops particularly in diverse real-world scenes. In this paper we propose a robust solution to turbulence removal from an RGB image under the guidance of an additional narrow-band image broadening the applicability of turbulence mitigation techniques in real-world imaging scenarios. Our approach exhibits a substantial suppression in the magnitude of turbulence artifacts by using only a pair of images thereby enhancing the clarity and fidelity of the captured scene.
Cite
Text
Xia et al. "NB-GTR: Narrow-Band Guided Turbulence Removal." Conference on Computer Vision and Pattern Recognition, 2024. doi:10.1109/CVPR52733.2024.02355Markdown
[Xia et al. "NB-GTR: Narrow-Band Guided Turbulence Removal." Conference on Computer Vision and Pattern Recognition, 2024.](https://mlanthology.org/cvpr/2024/xia2024cvpr-nbgtr/) doi:10.1109/CVPR52733.2024.02355BibTeX
@inproceedings{xia2024cvpr-nbgtr,
title = {{NB-GTR: Narrow-Band Guided Turbulence Removal}},
author = {Xia, Yifei and Zhou, Chu and Zhu, Chengxuan and Teng, Minggui and Xu, Chao and Shi, Boxin},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2024},
pages = {24934-24943},
doi = {10.1109/CVPR52733.2024.02355},
url = {https://mlanthology.org/cvpr/2024/xia2024cvpr-nbgtr/}
}