UNSUPERVISED AND UNTRAINED UNDERWATER IMAGE RESTORATION BASED ON PHYSICAL IMAGE FORMATION MODEL

We propose an unsupervised and untrained underwater image restoration method based on the layer disentanglement and the underwater image formation model.

Dependencies

• Python == 3.6.10
• Pytorch == 1.1.0
• opencv-python == 3.4.2.16
• opencv-contrib-python == 3.4.2.16

We also export our conda virtual environment as UIE.yaml. You can use the following command to create the environment.

conda env create -f UIE.yaml

Demo

You can use the following command:

python main.py

Bibtex

@inproceedings{chai2022unsupervised,
  title={Unsupervised and Untrained Underwater Image Restoration Based on Physical Image Formation Model},
  author={Chai, Shu and Fu, Zhenqi and Huang, Yue and Tu, Xiaotong and Ding, Xinghao},
  booktitle={ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages={2774--2778},
  year={2022},
  organization={IEEE}
}