Zhendong Wang, Xiaodong Cun, Jianmin Bao, Wengang Zhou, Jianzhuang Liu, Houqiang Li

Paper: https://arxiv.org/abs/2106.03106

• 2022.04.09 Upload results of Uformer on denoising (SIDD, DND), motion deblurring (GoPro, HIDE, RealBlur-J/-R), and defocus deblurring (DPDD).
• 2022.03.02 Uformer has been accepted by CVPR 2022! 🔥
• 2021.11.30 Update Uformer in Arxiv link. The new code, models and results will be uploaded.
• 2021.10.28 Release the results of Uformer32 on SIDD and DND.
• 2021.09.30 Release pre-trained Uformer16 for SIDD denoising.
• 2021.08.19 Release a pre-trained model(Uformer32)! Add a script for FLOP/GMAC calculation.
• 2021.07.29 Add a script for testing the pre-trained model on the arbitrary-resolution images.

The project is built with PyTorch 1.7.1, Python3.7, CUDA10.1. For package dependencies, you can install them by:

pip install -r requirements.txt

• Uformer32_denoising_sidd.pth [Google Drive]: PSNR 39.77 dB.
• Uformer16_denoising_sidd.pth [Google Drive]: PSNR 39.65 dB.

• Uformer_B: SIDD | DND | GoPro | HIDE | RealBlur-J | RealBlur-R | DPDD
• Uformer32: SIDD | DND

For training data of SIDD, you can download the SIDD-Medium dataset from the official url. Then generate training patches for training by:

python3 generate_patches_SIDD.py --src_dir ../SIDD_Medium_Srgb/Data --tar_dir ../datasets/denoising/sidd/train

For evaluation, we use the same evaluation data as here, and put it into the dir ../datasets/denoising/sidd/val.

To train Uformer32(embed_dim=32) on SIDD, we use 2 V100 GPUs and run for 250 epochs:

python3 ./train.py --arch Uformer --batch_size 32 --gpu '0,1' \
    --train_ps 128 --train_dir ../datasets/denoising/sidd/train --env 32_0705_1 \
    --val_dir ../datasets/denoising/sidd/val --embed_dim 32 --warmup

More configuration can be founded in train.sh.

To evaluate Uformer32 on SIDD, you can run:

python3 ./test.py --arch Uformer --batch_size 1 --gpu '0' \
    --input_dir ../datasets/denoising/sidd/val --result_dir YOUR_RESULT_DIR \
    --weights YOUR_PRETRAINED_MODEL_PATH --embed_dim 32 

We provide a simple script to calculate the flops by ourselves, a simple script has been added in model.py. You can change the configuration and run it via:

python3 model.py

The manual calculation of GMacs in this repo differs slightly from the main paper, but they do not influence the conclusion. We will correct the paper later.

If you find this project useful in your research, please consider citing:

@inproceedings{Wang2022Uformer,
	title={Uformer: A General U-Shaped Transformer for Image Restoration},
	author={Wang, Zhendong and Cun, Xiaodong and Bao, Jianmin and Zhou, Wengang and Liu, Jianzhuang and Li, Houqiang},
	booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
	year={2022}
}

This code borrows heavily from MIRNet and SwinTransformer.

Please contact us if there is any question or suggestion(Zhendong Wang [email protected], Xiaodong Cun [email protected]).