Skip to content

Code for 2021 CVPR submission: CT Film Recovery via Disentangling Geometric Deformation and Photometric Degradation: Simulated Datasets and Deep Models

License

Notifications You must be signed in to change notification settings

transcendentsky/Film-Recovery

Repository files navigation

CT Film Recovery Network

dataset link: coming soon

Usage

Environment

python == 3.6 
pytorch == 1.6.0 
torchvison == 0.6

Data preparation

We train/test our model on CTFilm20K Datasets

We expect the directory structure to be the following:

path/to/CTFilm20K
    img/
        xxx.png
        xxx.png
        ...
    3dmap/
    albedo/
    depth/
    shader_normal/
    uv/

Training

To train our model, run this script

python -m scripts.misc.train_unwarp.py

To evalutate our model, run this script

python -m scripts.misc.train_unwarp --test

License

This code is released under the Apache 2.0 license. Please see the LICENSE file for more information.

About

Code for 2021 CVPR submission: CT Film Recovery via Disentangling Geometric Deformation and Photometric Degradation: Simulated Datasets and Deep Models

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages