This repository is built upon QARV and NTSCC, thanks very much!

@article{zhang2024learned,
  title={Learned Image Transmission with Hierarchical Variational Autoencoder},
  author={Zhang, Guangyi and Li, Hanlei and Cai, Yunlong and Hu, Qiyu and Yu, Guanding and Zhang, Runmin},
  booktitle={The 39th Annual AAAI Conference on Artificial Intelligence},
  year={2024}
}

Clone this repository and enter the directory using the commands below:

git clone https://github.com/zhang-guangyi/HJSCC.git
cd HJSCC/

Python 3.9.21 is recommended.

Install the required packages with:

pip install -r requirements.txt 

If you're having issues with installing PyTorch compatible with your CUDA version, we strongly recommend related documentation page.

• Two pre-trained models are provided in the HJSCC/checkpoint and HJSCC_feedback/checkpoint folder, and can be found in the link.

In net.py. please set as: for quality_1 lmb=512 while for quality_2 lmb=1024