Counting 2,899 Big Data & Machine Learning Frameworks, Toolsets, and Examples...
Suggestion? Feedback? Tweet @stkim1

Last Commit
Jun. 23, 2018
Apr. 26, 2017


arXiv Paper Version

Pytorch implementation of the paper DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks.

Our network takes blurry image as an input and procude the corresponding sharp estimate, as in the example:

The model we use is Conditional Wasserstein GAN with Gradient Penalty + Perceptual loss based on VGG-19 activations. Such architecture also gives good results on other image-to-image translation problems (super resolution, colorization, inpainting, dehazing etc.)

How to run


  • NVIDIA GPU + CUDA CuDNN (CPU untested, feedback appreciated)
  • Pytorch

Download weights from Dropbox . Note that during the inference you need to keep only Generator weights.

Put the weights into


To test a model put your blurry images into a folder and run:

python --dataroot /.path_to_your_data --model test --dataset_mode single --learn_residual


Download dataset for Object Detection benchmark from Google Drive


If you want to train the model on your data run the following command to create image pairs:

python datasets/ --fold_A /path/to/data/A --fold_B /path/to/data/B --fold_AB /path/to/data

And then the following command to train the model

python --dataroot /.path_to_your_data --learn_residual --resize_or_crop crop --fineSize CROP_SIZE (we used 256)

Other Implementations

Keras Blog

Keras Repository


If you find our code helpful in your research or work please cite our paper.

  title = {DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks},
  author = {Kupyn, Orest and Budzan, Volodymyr and Mykhailych, Mykola and Mishkin, Dmytro and Matas, Jiri},
  journal = {ArXiv e-prints},
  eprint = {1711.07064},
  year = 2017


Code borrows heavily from pix2pix. The images were taken from GoPRO test dataset - DeepDeblur