MAGC: Map-Assisted Remote-Sensing Image Compression at Extremely Low Bitrates

Official code for Paper

📖Table Of Contents

• Compression Performance
• Installation
• Pretrained Models
• Dataset
• Inference
• Train

👀Compression Performance

Quantitative Comparisons

Qualitative Comparisons

⚙️Installation

# clone this repo
git clone https://github.com/WHUyyx/MAGC.git

# create an environment with python >= 3.9
conda create -n MAGC python=3.9
conda activate MAGC
pip install -r requirements.txt

🧬Pretrained Models

Please download the pretrained model from Google Drive and place it in the magc_ckpts/ckpts_stage2/ folder for inference.

🧗Dataset

Please access the training set and test set from SGDM.

⚔️Inference

CUDA_VISIBLE_DEVICES=0 python inference.py \
--ckpt magc_ckpts/ckpts_stage2/v40_step=120999-lpips=0.3132.ckpt \
--config configs/model/cldm.yaml \
--input_path ../dataset/Synthetic-v18-45k/test_4500 \
--steps 50 \
--batchsize 30 \
--output_root metrics_4500_magc \
--device cuda    

🌠Train

TBD

Citation

Please cite us if our work is useful for your research.

@misc{ye2024map,
      title={Map-Assisted Remote-Sensing Image Compression at Extremely Low Bitrates}, 
      author={Yixuan Ye and Ce Wang and Wanjie Sun and Zhenzhong Chen},
      year={2024},
      eprint={2409.01935},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Acknowledgement

This project is based on DiffBIR and CompressAI. Thanks for their awesome work.

Contact

If you have any questions, please feel free to contact with me at yeyixuan@whu.edu.cn.