Text-Guided Token Communication for Wireless Image Transmission

2025/07/08 by Liu, Bole, Qiao, Li, Wang, Ye +4 · 3 citations
#FOS: Computer and information sciences #Information Theory (cs.IT)

paper · doi:10.48550/arxiv.2507.05781

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.

Citations

• ToDMA: Large Model-Driven Massive Token Communications for Semantic Multiple Access
• Semantic Packet Aggregation for Token Communication via Genetic Beam Search
• Token Communications: A Large Model-Driven Framework for Cross-modal Context-aware Semantic Communications
• Token-Domain Multiple Access: Exploiting Semantic Orthogonality for Collision Mitigation
• Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens
• Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models
• Deep Joint Semantic Coding and Beamforming for Near-Space Airship-Borne Massive MIMO Network
• Latency-Aware Generative Semantic Communications with Pre-Trained Diffusion Models
• Near-Space Communications: the Last Piece of 6G Space-Air-Ground-Sea Integrated Network Puzzle
• Hybrid Knowledge-Data Driven Channel Semantic Acquisition and Beamforming for Cell-Free Massive MIMO
• Muse: Text-To-Image Generation via Masked Generative Transformers
• DeepJSCC-Q: Constellation Constrained Deep Joint Source-Channel Coding
• Transformer-Empowered 6G Intelligent Networks: From Massive MIMO Processing to Semantic Communication
• Learning Transferable Visual Models From Natural Language Supervision
• Taming Transformers for High-Resolution Image Synthesis
• Wireless Image Transmission Using Deep Source Channel Coding With Attention Modules
• The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
• Neural Discrete Representation Learning

Cited by

• GenED-SC: Generative Editing Semantic Communication with Integrated Multi-Modal LLMs
• Context-Aware Search and Retrieval Under Token Erasure
• Geometric Cross-Modal Token Selection for Latency-Constrained Multimodal Token Communication

Related

• ResiTok: A Resilient Tokenization-Enabled Framework for Ultra-Low-Rate and Robust Image Transmission
• Text-Guided Diffusion Model-based Generative Communication for Wireless Image Transmission
• Semantic-Aware Visual Information Transmission With Key Information Extraction Over Wireless Networks
• Vision Transformer Based Semantic Communications for Next Generation Wireless Networks
• Adaptive Wireless Image Semantic Transmission: Design, Simulation, and Prototype Validation