An Image Semantic Communication System Based on GAN and Relative Position-Encoding

IF 4.4 3区计算机科学 Q2 TELECOMMUNICATIONS

IEEE Communications Letters Pub Date : 2025-04-09 DOI:10.1109/LCOMM.2025.3559202

Ziqi Zhang;Weijie Tan;Chunguo Li

引用次数: 0

Abstract

In image semantic communication, the complex wireless channel environment leads to the loss of image details and performance degradation during transmission. To address this issue, we propose an image semantic communication system based on Generative Adversarial Networks (GAN) and Relative Position-Encoding (RPE), named GAN-RpeSC. Specifically, in the system design, we introduce the GAN network at the output of the semantic communication framework to enhance the image restoration. We integrate the RPE module into the Visual Transformer (ViT) module, adding the RPE module to its Multihead Self Attention (MHSA), so that the model can better capture the spatial location information of the image. Experimental results show that the proposed GAN-RpeSC has significant advantages in improving image transmission quality, with a 0.3 dB improvement in peak signal-to-noise ratio (PSNR) compared to the ViT module alone.

查看原文本刊更多论文

基于GAN和相对位置编码的图像语义通信系统

在图像语义通信中，复杂的无线信道环境会导致图像细节的丢失和传输过程中的性能下降。为了解决这个问题，我们提出了一个基于生成对抗网络（GAN）和相对位置编码（RPE）的图像语义通信系统，命名为GAN- rpesc。具体来说，在系统设计中，我们在语义通信框架的输出端引入GAN网络来增强图像的复原能力。我们将RPE模块集成到Visual Transformer （ViT）模块中，将RPE模块添加到其Multihead Self Attention （MHSA）模块中，使模型能够更好地捕获图像的空间位置信息。实验结果表明，GAN-RpeSC在提高图像传输质量方面具有显著优势，与单独的ViT模块相比，峰值信噪比（PSNR）提高了0.3 dB。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Communications Letters 工程技术-电信学

CiteScore

8.10

自引率

7.30%

发文量

590

审稿时长

2.8 months

期刊介绍： The IEEE Communications Letters publishes short papers in a rapid publication cycle on advances in the state-of-the-art of communication over different media and channels including wire, underground, waveguide, optical fiber, and storage channels. Both theoretical contributions (including new techniques, concepts, and analyses) and practical contributions (including system experiments and prototypes, and new applications) are encouraged. This journal focuses on the physical layer and the link layer of communication systems.