Graduation project for image restoration, enhancement & colorization.
Run setup.sh to download weights & models & stuff.
Run main.py to generate results. Input directory is sample_images, but you can change that (see run in main.py).
There's also a GUI app that's built with PySimpleGUI. See/run gui.py.
You can also download the project from this link. The link is hosted by PySimpleGUI. It includes the needed weights/models (about 4.5GB in total with the code). The GUI also looks nicer (e.g. it's modified to run the lengthy operations in another thread, so the GUI doesn't hang).
According to RunMode and whether colorize is set, output is either <output-dir>/face_restore or <output-dir>/quality_enh/restored_image
or <output-dir>/colorization (also see run in main.py).
- Supplant out-of-the-box face restoration in scratched photos with GPEN's face inpainting. Not sure if it'd work though. We'd have to blend in the restored face to the result of running vanilla scratch restoration.
