News

• Our new paper ID-Blau: Image Deblurring by Implicit Diffusion-based reBLurring AUgmentation (CVPR 2024) is avalable.
  
• Our new paper Domain-adaptive Video Deblurring via Test-time Blurring (ECCV 2024) is avalable.
  

Stripformer (ECCV 2022 Oral)

Pytorch Implementation of "Stripformer: Strip Transformer for Fast Image Deblurring" (ECCV 2022 Oral)

Installation

The implementation is modified from "DeblurGANv2".

git clone https://github.com/pp00704831/Stripformer.git
cd Stripformer
conda create -n Stripformer python=3.6
source activate Stripformer
conda install pytorch==1.8.0 torchvision==0.9.0 torchaudio==0.8.0 cudatoolkit=11.1 -c pytorch -c conda-forge
pip install opencv-python tqdm pyyaml joblib glog scikit-image tensorboardX albumentations
pip install -U albumentations[imgaug]
pip install albumentations==1.1.0

Training

Download "GoPro" dataset into './datasets'
For example: './datasets/GoPro'

We train our Stripformer in two stages:

• We pre-train Stripformer for 3000 epochs with patch size 256x256
  
• Run the following command

python train_Stripformer_pretrained.py

• After 3000 epochs, we keep training Stripformer for 1000 epochs with patch size 512x512
  
• Run the following command

python train_Stripformer_gopro.py

Testing

For reproducing our results on GoPro and HIDE datasets, download "Stripformer_gopro.pth"

For reproducing our results on RealBlur dataset, download "Stripformer_realblur_J.pth" and "Stripformer_realblur_R.pth"

For testing on GoPro dataset

• Download "GoPro" full dataset or test set into './datasets' (For example: './datasets/GoPro/test')
  
• Run the following command

python predict_GoPro_test_results.py --weights_path ./Stripformer_gopro.pth 

For testing on HIDE dataset

• Download "HIDE" into './datasets'
  
• Run the following command

python predict_HIDE_results.py --weights_path ./Stripformer_gopro.pth 

For testing on RealBlur test sets

• Download "RealBlur_J" and "RealBlur_R" into './datasets'
  
• Run the following command

python predict_RealBlur_J_test_results.py --weights_path ./Stripformer_realblur_J.pth 

python predict_RealBlur_R_test_results.py --weights_path ./Stripformer_realblur_R.pth 

For testing your own training weight (take GoPro for a example)

• Rename the path in line 23 in the predict_GoPro_test_results.py
  
• Chage command to --weights_path ./final_Stripformer_gopro.pth

Evaluation

• For evaluation on GoPro results in MATLAB, download "Stripformer_GoPro_results" into './out'

evaluation_GoPro.m

• For evaluation on HIDE results in MATLAB, download "Stripformer_HIDE_results" into './out'

evaluation_HIDE.m

• For evaluation on RealBlur_J results, download "Stripformer_realblur_J_results" into './out'

python evaluate_RealBlur_J.py

• For evaluation on RealBlur_R results, download "Stripformer_realblur_R_results" into './out'

python evaluate_RealBlur_R.py

Citation

@inproceedings{Tsai2022Stripformer,
  author    = {Fu-Jen Tsai and Yan-Tsung Peng and Yen-Yu Lin and Chung-Chi Tsai and Chia-Wen Lin},
  title     = {Stripformer: Strip Transformer for Fast Image Deblurring},
  booktitle = {ECCV},
  year      = {2022}
}