DPHSIR

Paper | Pretrained Model

Deep Plug-and-Play Prior for Hyperspectral Image Restoration (Neurocomputing 2022)

Zeqiang Lai, Kaixuan Wei, Ying Fu

News ✨

• 2021-01-22: Add a command line client for testing single image or list of images in folders.
• 2021-01-21: Release demo code for each task.

Usages

1. Install the requirments

# Pytorch >= 1.8
conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch
conda install -c conda-forge opencv
pip install -r requirements.txt

2. Clone the repo

git clone https://github.com/Zeqiang-Lai/DPHSIR.git
cd DPHSIR
pip install -e .

3. Run cli or playgrounds

• Download the sample input if you don't have one.
• Download the pretrained model, grunet.pth, put it in playgrounds/grunet.pth.

# run cli
python cli/main.py -i [input_path] [task]
# run playground
python playgrounds/deblur.py

Citation

If you find our work useful for your research, please consider citing our paper :)

@article{lai2022dphsir,
    title = {Deep plug-and-play prior for hyperspectral image restoration},
    journal = {Neurocomputing},
    volume = {481},
    pages = {281-293},
    year = {2022},
    issn = {0925-2312},
    doi = {https://doi.org/10.1016/j.neucom.2022.01.057},
    author = {Zeqiang Lai and Kaixuan Wei and Ying Fu},
}

Acknowledgement

• We use some code from DPIR.
• The training code of GRUNet is QRNN3D