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

update citation&info of NAFSSR

pull/96/head
achusky 2022-06-30 20:48:45 +08:00
parent 9d0ddcc715
commit 23793577a6
2 changed files with 27 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
docs/StereoSR.md
View File

@ -1,7 +1,7 @@
## NAFSSR: Stereo Image Super-Resolution Using NAFNet
The official pytorch implementation of the paper **[NAFSSR: Stereo Image Super-Resolution Using NAFNet](https://arxiv.org/abs/2204.08714)**
The official pytorch implementation of the paper **[NAFSSR: Stereo Image Super-Resolution Using NAFNet](https://arxiv.org/abs/2204.08714)**.
You can get more infomation about NAFSSR with folloing links: [[video](https://drive.google.com/file/d/16w33zrb3UI0ZIhvvdTvGB2MP01j0zJve/view)]/[[slides](https://data.vision.ee.ethz.ch/cvl/ntire22/slides/Chu_NAFSSR_slides.pdf)]/[[poster](https://data.vision.ee.ethz.ch/cvl/ntire22/posters/Chu_NAFSSR_poster.pdf)].
#### Xiaojie Chu\*, Liangyu Chen\*, Wenqing Yu
>This paper proposes a simple baseline named NAFSSR for stereo image super-resolution. We use a stack of NAFNet's Block (NAFBlock) for intra-view feature extraction and combine it with Stereo Cross Attention Modules (SCAM) for cross-view feature interaction.
@ -137,3 +137,16 @@ python -m torch.distributed.launch --nproc_per_node=1 --master_port=4321 basicsr
## Citations
If NAFSSR helps your research or work, please consider citing NAFSSR.
```
@InProceedings{chu2022nafssr,
author = {Chu, Xiaojie and Chen, Liangyu and Yu, Wenqing},
title = {NAFSSR: Stereo Image Super-Resolution Using NAFNet},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2022},
pages = {1239-1248}
}
```

13
readme.md
View File

@ -26,7 +26,7 @@ The official pytorch implementation of the paper **[Simple Baselines for Image R
![PSNR_vs_MACs](./figures/PSNR_vs_MACs.jpg)
### News
**2022.04.15** NAFNet based Stereo Image Super-Resolution solution ([NAFSSR](https://arxiv.org/abs/2204.08714)) won the **1st place** on the NTIRE 2022 Stereo Image Super-resolution Challenge! Training/Evaluation instructions see [here](https://github.com/megvii-research/NAFNet/blob/main/docs/StereoSR.md).
**2022.04.15** NAFNet based Stereo Image Super-Resolution solution ([NAFSSR](https://arxiv.org/abs/2204.08714)) won the **1st place** on the NTIRE 2022 Stereo Image Super-resolution Challenge! Training/Evaluation instructions see [here](https://github.com/megvii-research/NAFNet/blob/main/docs/StereoSR.md). [Presentation video](https://drive.google.com/file/d/16w33zrb3UI0ZIhvvdTvGB2MP01j0zJve/view), [slides](https://data.vision.ee.ethz.ch/cvl/ntire22/slides/Chu_NAFSSR_slides.pdf) and [poster](https://data.vision.ee.ethz.ch/cvl/ntire22/posters/Chu_NAFSSR_poster.pdf) are available now.
### Installation
This implementation based on [BasicSR](https://github.com/xinntao/BasicSR) which is a open source toolbox for image/video restoration tasks and [HINet](https://github.com/megvii-model/HINet)
@ -109,6 +109,17 @@ If NAFNet helps your research or work, please consider citing NAFNet.
year={2022}
}
```
If NAFSSR helps your research or work, please consider citing NAFSSR.
```
@InProceedings{chu2022nafssr,
author = {Chu, Xiaojie and Chen, Liangyu and Yu, Wenqing},
title = {NAFSSR: Stereo Image Super-Resolution Using NAFNet},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2022},
pages = {1239-1248}
}
```
### Contact