Improved Nonlinear Transform Source-Channel Coding to Catalyze Semantic Communications [pdf]
This is the repository of the paper "Improved Nonlinear Transform Source-Channel Coding to Catalyze Semantic Communications".
Evaluation on Kodak Dataset
Evaluation on CLIC 2021 testset
Clone the repo and create a conda environment (we use PyTorch 1.9, CUDA 11.1).
The dependencies includes CompressAI, Natten, and timm.
Download the pre-trained models from Google Drive.
Note: We reorganize code and the performances are slightly different from the paper's.
Evaluate:
# Kodak
python main.py --gpu-id 0 --test-only --eval-dataset-path /path/to/kodak --eval-dataset-name kodak --pretrained /path/to/checkpoint
Release the code for online inference (NTSCC++)
Codebase from CompressAI, TinyLIC, and Swin Transformer
If you find this code useful for your research, please cite our paper
@inproceedings{
wang2023improved,
title={Improved Nonlinear Transform Source-Channel Coding to Catalyze Semantic Communications},
author={Sixian Wang and Jincheng Dai and Xiaoqi Qin and Zhongwei Si and Kai Niu and Ping Zhang},
year={2023},
booktitle={IEEE Journal of Selected Topics in Signal Processing, early access},
}