Awesome

Deblur_MCEM

The repo provides the demo code for the nonuniform deblurring method. For more efficient Langevin sampling, we provide the preconditioned gradient descent Langevin (p-LD) iteration, which is used in the demo code.

Requirement

All the codes are tested on Ubuntu LTS 18.04. Pls ensure the working OS system matches the required OS version.

Request the demo python file

The following two demo files are accessible upon the request at matliji@163.com.

Lai_nonuniform_cvpr_MCEM_pLD.py
Gopro_nonuniform_cvpr_MCEM_pLD.py

Reconstruction of Lai nonuniform dataset

You can access the forward_operator demo file and the reconstruction of the Lai nonuniform dataset at Google driver. The quantitative metric is also provided, where the rotation is taken into consideration.

Run the demo

For the Lai nonuniform dataset

```bash
python3 Lai_nonuniform_cvpr_MCEM_pLD.py
```

For the Gopro nonuniform deblurring

```bash
python3 Gopro_nonuniform_cvpr_MCEM_pLD.py
```

Citation

If you find our work useful in your research or publication, please cite it:

@inproceedings{li2023self,
  title={Self-Supervised Blind Motion Deblurring With Deep Expectation Maximization},
  author={Li, Ji and Wang, Weixi and Nan, Yuesong and Ji, Hui},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={13986--13996},
  year={2023}
}