Text-Guided Token Communication for Wireless Image Transmission

TL;DR

This paper introduces a text-guided token communication system for wireless image transmission that leverages pre-trained models, enabling high-quality, low-bandwidth image transfer with strong generalization and reduced cliff effects across various channel conditions.

Contribution

The proposed system uniquely combines token-based image encoding, 5G NR polar coding, and text-guided prediction, achieving superior perceptual quality without scenario-specific retraining.

Findings

Outperforms ADJSCC in perceptual quality and semantic preservation at SNRs above 0 dB.

Mitigates cliff effect at lower SNRs, maintaining image quality.

Exhibits strong cross-dataset generalization without retraining.

Abstract

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.