Skip to content
Code repo for "Spatio-Temporal Filter Adaptive Network for Video Deblurring" (ICCV'19)
Python Cuda C++ Shell
Branch: master
Clone or download
Latest commit 8810616 Oct 8, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
ckpt Create code repo for STFANet. Jul 19, 2019
core Create code repo for STFANet. Jul 19, 2019
datasets Create code repo for STFANet. Jul 19, 2019
losses Create code repo for STFANet. Jul 19, 2019
models Update the requirements for PyTorch. Jul 29, 2019
utils
.gitignore Create code repo for STFANet. Jul 19, 2019
LICENSE
README.md Update README.md Oct 8, 2019
config.py
install.sh Create code repo for STFANet. Jul 19, 2019
requirements.txt Update the requirements for PyTorch. Jul 29, 2019
run.sh Create code repo for STFANet. Jul 19, 2019
runner.py Create code repo for STFANet. Jul 19, 2019

README.md

STFAN

Code repo for the paper "Spatio-Temporal Filter Adaptive Network for Video Deblurring".  [arXiv]   [Project Page] 

Pretrained Models

You could download the pretrained model (21.5MB) of STFAN from [Here].

Prerequisites

  • Linux (tested on Ubuntu 14.04/16.04)
  • gcc 4.9+
  • Python 2.7+
  • Pytorch 0.4.1.post2
  • easydict
  • tensorboardX

Installation

pip install -r requirements.txt
bash install.sh

Get Started

Use the following command to train the neural network:

python runner.py 
        --phase 'train'\
        --data [dataset path]\
        --out [output path]

Use the following command to test the neural network:

python runner.py \
        --phase 'test'\
        --weights './ckpt/best-ckpt.pth.tar'\
        --data [dataset path]\
        --out [output path]

Use the following command to resume training the neural network:

python runner.py 
        --phase 'resume'\
        --weights './ckpt/best-ckpt.pth.tar'\
        --data [dataset path]\
        --out [output path]

You can also use the following simple command, with changing the settings in config.py:

python runner.py

Results on the testing dataset and real blurry videos

Some results are shown in [Project Page].

Citation

If you find STFANet, or FAC layer useful in your research, please consider citing:

@article{Zhou2019stfan,
  title={Spatio-Temporal Filter Adaptive Network for Video Deblurring},
  author={Zhou, Shangchen and Zhang, Jiawei and Pan, Jinshan and Xie, Haozhe and Zuo, Wangmeng and Ren, Jimmy},
  journal={arXiv preprint arXiv:1904.12257},
  year={2019}
}

Contact

We are glad to hear if you have any suggestions and questions.

Please send email to shangchenzhou@gmail.com

License

This project is open sourced under MIT license.

You can’t perform that action at this time.