Home

Awesome

Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Model

License: MIT

Paper Link: https://arxiv.org/abs/2207.10040

Authors: Zhiyuan Mao*, Ajay Jaiswal*, Zhangyang Wang, Stanley H. Chan

Official Pytorch Implementation of ECCV 2022

The Turbulence Text Dataset can be downloaded from: https://drive.google.com/file/d/1QWvQfPM-lJwGqK_Wm6lDbi-tYBu-Uopq/view?usp=sharing

The Heat Chamber Dataset can be downloaded from: https://drive.google.com/file/d/14iVachB95bCCtke8ONPD9CCH20JO75v2/view?usp=sharing

Our models will be released in the following location: https://drive.google.com/drive/folders/1ijaHurveoWKBJrpDAzpeqGtVy-9-36Pw?usp=sharing

This dataset was also used in the 5th UG2+ Prize Challenge in associated with the "Bridging the Gap Between Computational Photography and Visual Recognition Workshop" at CVPR 2022. http://cvpr2022.ug2challenge.org/

If you find our work helpful in your research, please cite our paper

Citation

If you find our code implementation helpful for your own resarch or work, please cite our paper.

@inproceedings{Mao2022SingleFA,
  title={Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Model},
  author={Zhiyuan Mao and Ajay Jaiswal and Zhangyang Wang and Stanley H. Chan},
  booktitle={European Conference on Computer Vision (ECCV)},
  year={2022}
}

Visit our website for more works and tutorials on Imaging through Atmospheric Turbulence https://engineering.purdue.edu/ChanGroup/project_turbulence.html