With the emergence of 6G networks and proliferation of visual applications, efficient image transmission under adverse channel conditions is critical. We present a text-guided token communication system leveraging pre-trained foundation models for wireless image transmission with low bandwidth. Our approach converts images to discrete tokens, applies 5G NR polar coding, and employs text-guided token prediction for reconstruction. Evaluations on ImageNet show our method outperforms Deep Source Channel Coding with Attention Modules (ADJSCC) in perceptual quality and semantic preservation at Signal-to-Noise Ratios (SNRs) above 0 dB while mitigating the cliff effect at lower SNRs. Our system requires no scenario-specific retraining and exhibits superior cross-dataset generalization, establishing a new paradigm for efficient image transmission aligned with human perceptual priorities.
@article{arxiv.2507.05781,
title = {Text-Guided Token Communication for Wireless Image Transmission},
author = {Bole Liu and Li Qiao and Ye Wang and Zhen Gao and Yu Ma and Keke Ying and Tong Qin},
journal= {arXiv preprint arXiv:2507.05781},
year = {2025}
}