Long Sun, Jiangxin Dong, Jinhui Tang, and Jinshan Pan
IMAG Lab, Nanjing University of Science and Technology
An overview of the proposed SAFMN. SAFMN first transforms the input LR image into the feature space using a convolutional layer, performs feature extraction using a series of feature mixing modules (FMMs), and then reconstructs these extracted features by an upsampler module. The FMM block is mainly implemented by a spatially-adaptive feature modulation (SAFM) layer and a convolutional channel mixer (CCM).
- Python 3.8, PyTorch >= 1.11
- BasicSR 1.4.2
- Platforms: Ubuntu 18.04, cuda-11
# Clone the repo
git clone https://github.com/sunny2109/SAFMN.git
# Install dependent packages
cd SAFMN
pip install -r requirements.txt
# Install BasicSR
python setup.py develop
You can also refer to this INSTALL.md for installation
Run the following commands for training:
# train SAFMN for x4 effieicnt SR
python basicsr/train.py -opt options/train/SAFMN/train_DF2K_x4.yml
# train SAFMN for x4 classic SR
python basicsr/train.py -opt options/train/SAFMN/train_L_DF2K_x4.yml
# test SAFMN for x4 efficient SR
python basicsr/test.py -opt options/test/SAFMN/test_benchmark_x4.yml
# test SAFMN for x4 classic SR
python basicsr/test.py -opt options/test/SAFMN/test_L_benchmark_x4.yml
# test SAFMN for x4 real-world SR (without ground-truth)
python basicsr/test.py -opt options/test/SAFMN/test_real_img_x4.yml
# test SAFMN for x4 real-world SR (large input)
python inference/inference_real_safmn.py --input test_demo --output results/test_demo --scale 4 --large_input
Pretrained models and visual results
We have provided three ways to download our checkpoints.
Degradation | Model Zoo | Visual Results |
---|---|---|
BI-Efficient SR | Google Drive/Baidu Netdisk with code: SAFM | Google Drive/Baidu Netdisk with code: SAFM |
BI-Classic SR | Google Drive/Baidu Netdisk with code: SAFM | Google Drive/Baidu Netdisk with code: SAFM |
x4 Real-world | Google Drive/Baidu Netdisk with code: SAFM |
Real-World Image (x4) | Real-ESRGAN | SwinIR | SAFMN (ours) |
---|---|---|---|
Efficient SR Results
Classic SR Results
If this work is helpful for your research, please consider citing the following BibTeX entry.
@inproceedings{sun2023safmn,
title={Spatially-Adaptive Feature Modulation for Efficient Image Super-Resolution},
author={Sun, Long and Dong, Jiangxin and Tang, Jinhui and Pan, Jinshan},
booktitle={ICCV},
year={2023}
}
This code is based on BasicSR toolbox. Thanks for the awesome work.
If you have any questions, please feel free to reach me out at cs.longsun@gmail.com