mirrors
/
NAFNet
mirror of https://github.com/megvii-research/NAFNet
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Update readme.md

pull/8/head
Chen Liangyu 2022-04-20 00:27:02 +08:00 committed by GitHub
parent e475757a39
commit 25cd8c419b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
readme.md
View File

@ -11,6 +11,10 @@ The official pytorch implementation of the paper **[Simple Baselines for Image R
>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=256 width=256 alt="NAFNet For Image Denoise"> | <img src="./figures/deblur.gif" height="256" alt="NAFNet For Image Deblur"> | <img src="./figures/StereoSR.gif" height="256" alt="NAFSSR For Stereo Image Super Resolution"> |
| :----------------------------------------------------------: | :----------------------------------------------------------: | :----------------------------------------------------------: |
| Denoise | Deblur | StereoSR([NAFSSR](https://github.com/megvii-research/NAFNet/blob/main/docs/StereoSR.md)) |
![PSNR_vs_MACs](./figures/PSNR_vs_MACs.jpg)
### News