NAFNet

NAFNet: Nonlinear Activation Free Network for Image Restoration

The official pytorch implementation of the paper Simple Baselines for Image Restoration (ECCV2022)

Liangyu Chen*, Xiaojie Chu*, Xiangyu Zhang, Jian Sun

Although there have been significant advances in the field of image restoration recently, the system complexity of the state-of-the-art (SOTA) methods is increasing as well, which may hinder the convenient analysis and comparison of methods. In this paper, we propose a simple baseline that exceeds the SOTA methods and is computationally efficient. To further simplify the baseline, we reveal that the nonlinear activation functions, e.g. Sigmoid, ReLU, GELU, Softmax, etc. are not necessary: they could be replaced by multiplication or removed. Thus, we derive a Nonlinear Activation Free Network, namely NAFNet, from the baseline. SOTA results are achieved on various challenging benchmarks, e.g. 33.69 dB PSNR on GoPro (for image deblurring), exceeding the previous SOTA 0.38 dB with only 8.4% of its computational costs; 40.30 dB PSNR on SIDD (for image denoising), exceeding the previous SOTA 0.28 dB with less than half of its computational costs.

| <img src="./figures/denoise.gif" height=224 width=224 alt="NAFNet For Image Denoise"> | <img src="./figures/deblur.gif" width=400 height=224 alt="NAFNet For Image Deblur"> | <img src="./figures/StereoSR.gif" height=224 width=326 alt="NAFSSR For Stereo Image Super Resolution"> | | :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: | | Denoise | Deblur | StereoSR(NAFSSR) |

News

2022.08.02 The Baseline, including the pretrained models and train/test configs, are available now.

2022.07.03 Related work, Improving Image Restoration by Revisiting Global Information Aggregation (TLC, a.k.a TLSC in our paper) is accepted by ECCV2022 :tada: . Code is available at https://github.com/megvii-research/TLC.

2022.07.03 Our paper is accepted by ECCV2022 :tada:

2022.06.19 NAFSSR (as a challenge winner) is selected for an ORAL presentation at CVPR 2022, NTIRE workshop :tada: Presentation video, slides and poster are available now.

2022.04.15 NAFNet based Stereo Image Super-Resolution solution (NAFSSR) won the 1st place on the NTIRE 2022 Stereo Image Super-resolution Challenge! Training/Evaluation instructions see here.

Installation

This implementation based on BasicSR which is a open source toolbox for image/video restoration tasks and HINet

python 3.9.5
pytorch 1.11.0
cuda 11.3

git clone https://github.com/megvii-research/NAFNet
cd NAFNet
pip install -r requirements.txt
python setup.py develop --no_cuda_ext

Quick Start

• Image Denoise Colab Demo: <a href="https://colab.research.google.com/drive/1dkO5AyktmBoWwxBwoKFUurIDn0m4qDXT?usp=sharing"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="google colab logo"></a>
• Image Deblur Colab Demo: <a href="https://colab.research.google.com/drive/1yR2ClVuMefisH12d_srXMhHnHwwA1YmU?usp=sharing"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="google colab logo"></a>
• Stereo Image Super-Resolution Colab Demo: <a href="https://colab.research.google.com/drive/1PkLog2imf7jCOPKq1G32SOISz0eLLJaO?usp=sharing"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="google colab logo"></a>
• Single Image Inference Demo:
  • Image Denoise:

  python basicsr/demo.py -opt options/test/SIDD/NAFNet-width64.yml --input_path ./demo/noisy.png --output_path ./demo/denoise_img.png
  

  • Image Deblur:

  python basicsr/demo.py -opt options/test/REDS/NAFNet-width64.yml --input_path ./demo/blurry.jpg --output_path ./demo/deblur_img.png
  

  • --input_path: the path of the degraded image
  • --output_path: the path to save the predicted image
  • pretrained models should be downloaded.
  • Integrated into Huggingface Spaces 🤗 using Gradio. Try out the Web Demo for single image restoration
• Stereo Image Inference Demo:
  • Stereo Image Super-resolution:

  python basicsr/demo_ssr.py -opt options/test/NAFSSR/NAFSSR-L_4x.yml \
  --input_l_path ./demo/lr_img_l.png --input_r_path ./demo/lr_img_r.png \
  --output_l_path ./demo/sr_img_l.png --output_r_path ./demo/sr_img_r.png
  

  • --input_l_path: the path of the degraded left image
  • --input_r_path: the path of the degraded right image
  • --output_l_path: the path to save the predicted left image
  • --output_r_path: the path to save the predicted right image
  • pretrained models should be downloaded.
  • Integrated into Huggingface Spaces 🤗 using Gradio. Try out the Web Demo for stereo image super-resolution
• Try the web demo with all three tasks here:

Results and Pre-trained Models

| name | Dataset|PSNR|SSIM| pretrained models | configs | |:----|:----|:----|:----|:----|-----| |NAFNet-GoPro-width32|GoPro|32.8705|0.9606|gdrive | 百度网盘|[train](./options/train/GoPro/NAFNet-widt