Awesome
Contourlet Residual for Prompt Learning Enhanced Infrared Image Super-Resolution (CoRPLE)
This repo is the official implementation of, “Contourlet Residual for Prompt Learning Enhanced Infrared Image Super-Resolution”, Xingyuan Li, Jinyuan Liu*, Zhixin Chen, Yang Zou, Long Ma, Xin Fan, Risheng Liu, European Conference on Computer Vision (ECCV), 2024.
[pretrained models] [paper link]
🤖 Download
Download our datasets of infrared image super-resolution with detection labels. Original images are provided by TarDAL.
Download our datasets of infrared image super-resolution with segmentation labels. Original images are provided by SegMiF.
Dependencies
- Python 3.8
- PyTorch 1.8.0
- NVIDIA GPU + CUDA
# Clone the github repo and go to the default directory 'CoRPLE'.
git clone https://github.com/hey-it-s-me/CoRPLE.git
conda create -n CoRPLE python=3.8
conda activate CoRPLE
pip install -r requirements.txt
python setup.py develop
Training
- Run the following scripts. The training configuration is in
options/train/
.python basicsr/train.py -opt options/Train/train_CoRPLE_light_x2.yml python basicsr/train.py -opt options/Train/train_CoRPLE_light_x4.yml
- The training experiment is in
experiments/
.
Testing
- Run the following scripts. The testing configuration is in
options/test/
.python basicsr/train.py -opt options/Test/my_test_CoRPLE_light_x2.yml python basicsr/train.py -opt options/Test/my_test_CoRPLE_light_x4.yml
- The output is in
results/
.
Acknowledgements
This code is built on DAT and Contourlet-CNN .
Citation
If this work has been helpful to you, please feel free to cite our paper!
@inproceedings{li2024contourlet,
title={Contourlet Residual for Prompt Learning Enhanced Infrared Image Super-Resolution},
author={Li, Xingyuan and Liu, Jinyuan and Chen, Zhixin and Zou, Yang and Ma, Long and Fan, Xin and Liu, Risheng},
booktitle={European Conference on Computer Vision},
pages={270--288},
year={2024}
}
}