Skip to content
Keras implementation of "DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks"
Python
Branch: master
Clone or download
Latest commit 99446b0 Jun 28, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
deblurgan cleanup Nov 10, 2018
requirements cleanup Nov 10, 2018
sample add sample result Nov 10, 2018
scripts Update deblur_image.py Jun 28, 2019
.gitignore add gitignore Nov 9, 2018
README.md Update README.md Jun 28, 2019
generator.h5 update new weights file Nov 8, 2018
setup.py cleanup Nov 10, 2018

README.md

What is this repo ?

This repository is a Keras implementation of Deblur GAN. You can find a tutorial on how it works on Medium. Below is a sample result (from left to right: sharp image, blurred image, deblurred image)

Sample results

Installation

virtualenv venv -p python3
. venv/bin/activate
pip install -r requirements/requirements.txt
pip install -e .

Dataset

Get the GOPRO dataset, and extract it in the deblur-gan directory. The directory name should be GOPRO_Large.

Use:

python scripts/organize_gopro_dataset.py --dir_in=GOPRO_Large --dir_out=images

Training

python scripts/train.py --n_images=512 --batch_size=16 --log_dir /path/to/log/dir

Use python scripts/train.py --help for all options

Testing

python scripts/test.py

Use python scripts/test.py --help for all options

Deblur your own image

python scripts/deblur_image.py --weight_path=/path/to/generator.h5 --input_dir=/path/to/image/dir --output_dir=/path/to/deblurred/dir
You can’t perform that action at this time.