Text-Guided Diffusion Model-based Generative Communication for Wireless Image Transmission

TL;DR

This paper introduces a diffusion model-based generative communication framework for wireless image transmission that preserves semantic content and perceptual quality at extremely low data rates, outperforming traditional methods.

Contribution

It presents a novel joint source channel coding approach combined with semantic-guided generative reconstruction using diffusion models, enabling high-quality image recovery under severe bandwidth constraints.

Findings

Outperforms conventional coding schemes in perceptual quality.

Achieves robust image reconstruction across various channel conditions.

Utilizes semantic guidance for meaningful visual recovery.

Abstract

Reliable image transmission over wireless channels is particularly challenging at extremely low transmission rates, where conventional compression and channel coding schemes fail to preserve adequate visual quality. To address this issue, we propose a generative communication framework based on diffusion models, which integrates joint source channel coding (JSCC) with semantic-guided reconstruction leveraging a pre-trained generative model. Unlike conventional architectures that aim to recover exact pixel values of the original image, the proposed method focuses on preserving and reconstructing semantically meaningful visual content under severely constrained rates, ensuring perceptual plausibility and faithfulness to the scene intent. Specifically, the transmitter encodes the source image via JSCC and jointly transmits it with a textual prompt over the wireless channel. At the receiver, the corrupted low-rate representation is fused with the prompt and reconstructed through a Stable Diffusion model with ControlNet, enabling high-quality visual recovery. Leveraging both generative priors and semantic guidance, the proposed framework produces perceptually convincing images even under extreme bandwidth limitations. Experimental results demonstrate that the proposed method consistently outperforms conventional coding-based schemes and deep learning baselines, achieving superior perceptual quality and robustness across various channel conditions.