Skip to content

Latest commit

 

History

History
41 lines (32 loc) · 1.69 KB

README.md

File metadata and controls

41 lines (32 loc) · 1.69 KB
Raw

Offical PyTorch code for "Photon-Limited Blind Deconvolution Using Unsupervised Iterative Kernel Estimation"

Blind-Deconv-Figure

Instructions

  1. Create a local copy of repository using the following commands

    foor@bar:~$ git clone https://github.com/sanghviyashiitb/photon-limited-blind.git
foor@bar:~$ cd photon-limited-blind
foor@bar:~/photon-limited-blind$

  2. Download the pretrained models, i.e. denoiser and p4ip into model_zoo from the link here

  3. Download the zip file containing Levin dataset into the main directory and unzip using the following command:

    foo@bar:~/photon-limited-blind$ unzip levin.zip -d data/

  4. To test the network using real data, run the file

    foo@bar:~/poisson-deblurring$ python3 demo_deconv.py

    demo_real

Citation

@ARTICLE{9982288,
 author={Sanghvi, Yash and Gnanasambandam, Abhiram and Mao, Zhiyuan and Chan, Stanley H.},
 journal={IEEE Transactions on Computational Imaging}, 
 title={Photon-Limited Blind Deconvolution Using Unsupervised Iterative Kernel Estimation}, 
 year={2022},
 volume={8},
 number={},
 pages={1051-1062},
 doi={10.1109/TCI.2022.3226947}}

Feel free to ask your questions/share your feedback at [email protected]