Awesome

Remote Sensing Super-resolution Model Collection

The code of paper: GCRDN: Global Context-Driven Residual Dense Network for Remote Sensing Image Super-Resolution

Usage

Train

You could change all the setting in the option.py through form of '--xxx xxx' during training and testing such as:

python src/main.py --model your_model_name --save your_save_dir_name

The project also contains serval methods except from gcrdn including rdn, nlsn, rcan, dbpn, edrn, esrt, swinir, transms. The code of gcrdn is presented at src/model/gcrdn/mymodel.py

• RDN : Residual Dense Network for Image Super-Resolution

• NLSN : Image Super-Resolution with Non-Local Sparse Attention

• RCAN : Image Super-Resolution Using Very Deep Residual Channel Attention Networks

• DBPN : Deep Back-Projection Networks For Super-Resolution

• EDRN : Encoder-Decoder Residual Network for Real Super-resolution

• ESRT : Transformer for Single Image Super-Resolution

• SwinIR : SwinIR: Image Restoration Using Swin Transformer

• TranSMS : TranSMS: Transformers for Super-Resolution Calibration in Magnetic Particle Imaging

Test

1. Put pre-trained model into 'pre_train'
2. Change the model name in the option.py or use '--model your_model_name' :

python src/test.py --model your_model_name --save your_save_dir_name

My pretrained files on OLI2MSI of all models mentioned above are uploaded which could be gained from https://pan.baidu.com/s/1Zw8Vww-dLX_sRHYVdtQBww code: been

Dataset

The experimental datasets, OLI2MSI and Alsat, could be obtained from:

• OLI2MSI

• Alsat

I make few manipulation based on them. The processed datasets could be downloaded at https://pan.baidu.com/s/1l2CXgEJGVBGcOonUBnOLfg code bean.

Env

pytorch==1.13.0

cuda==11.7

python==3.10.6

Cite

Please cite this paper :)

@ARTICLE{10115440,
  author={Sui, Jialu and Ma, Xianping and Zhang, Xiaokang and Pun, Man-On},
  journal={IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing}, 
  title={GCRDN: Global Context-Driven Residual Dense Network for Remote Sensing Image Superresolution}, 
  year={2023},
  volume={16},
  number={},
  pages={4457-4468},
  doi={10.1109/JSTARS.2023.3273081}}

@article{sui2024denoising,
  title={Denoising Diffusion Probabilistic Model with Adversarial Learning for Remote Sensing Super-Resolution},
  author={Sui, Jialu and Wu, Qianqian and Pun, Man-On},
  journal={Remote Sensing},
  volume={16},
  number={7},
  pages={1219},
  year={2024},
  publisher={MDPI}
}

@article{sui2024adaptive,
  title={Adaptive Semantic-Enhanced Denoising Diffusion Probabilistic Model for Remote Sensing Image Super-Resolution},
  author={Sui, Jialu and Ma, Xianping and Zhang, Xiaokang and Pun, Man-On},
  journal={arXiv preprint arXiv:2403.11078},
  year={2024}
}

If you have any questions, be free to contact me!