Pre trained models!

[aligoglos]

You won't have plan to release pre trained models?

[csdwren]

The trained models have been released at OneDrive and BaiduYun. Please refer to the "readme.docx" in "results/levin/" and "results/lai/".
"SelfDeblur.zip" contains deblurred images and trained models. The links to OneDrive seem to have some problems. I will check it later.

[csdwren]

I have uploaded the trained models and fixed the OneDrive links.

You can refer to README "Getting Started -> 1. Run SelfDeblur -> (4) Reproduce ..." to load these trained models for reproducing the results reported in the paper.