NAFNet: Nonlinear Activation Free Network for Image Restoration

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

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.

News

NAFNet based Stereo Image Super-Resolution solution won the 1st place on the NTIRE 2022 Stereo Image Super-resolution Challenge! Coming Soon.

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:
• Image Deblur Colab Demo:
• 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/GoPro/NAFNet-width64.yml --input_path ./demo/blurry.png --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.

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 (提取码: so6v)	train | test
NAFNet-GoPro-width64	GoPro	33.7103	0.9668	gdrive | 百度网盘 (提取码: wnwh)	train | test
NAFNet-SIDD-width32	SIDD	39.9672	0.9599	gdrive | 百度网盘 (提取码: um97)	train | test
NAFNet-SIDD-width64	SIDD	40.3045	0.9614	gdrive | 百度网盘 (提取码: dton)	train | test
NAFNet-REDS-width64	REDS	29.0903	0.8671	gdrive | 百度网盘 (提取码: 9fas)	train | test

Image Restoration Tasks

Task	Dataset	Instructions	Visualization Results
Image Deblurring	GoPro	link	gdrive | 百度网盘 (提取码: 96ii)
Image Denoising	SIDD	link	gdrive | 百度网盘 (提取码: hu4t)
Image Deblurring with JPEG artifacts	REDS	link	gdrive | 百度网盘 (提取码: put5)

Citations

If NAFNet helps your research or work, please consider citing NAFNet.

@article{chen2022simple,
  title={Simple Baselines for Image Restoration},
  author={Chen, Liangyu and Chu, Xiaojie and Zhang, Xiangyu and Sun, Jian},
  journal={arXiv preprint arXiv:2204.04676},
  year={2022}
}

Contact

If you have any questions, please contact chenliangyu@megvii.com or chuxiaojie@megvii.com

---

statistics