Diffusion Model-Enabled Intelligent Channel Denoising for UAV Semantic Communication

Semantic communication (SC), by compressing raw data at the semantic level, significantly improves the information entropy of transmitted data and is considered as one of the key enabling technologies for the next-generation communication. However, most current research underestimates the impact of channel interference on SC systems. As an innovative generative artificial intelligence technique, the diffusion model (DM) has demonstrated remarkable performance in image denoising and enhancement. In this paper, we focus on the effects of wireless channels on SC image transmission and propose an unmanned aerial vehicle (UAV)-enhanced SC framework, termed diffusion joint source-channel coding (D-JSCC). Initially, we deploy a ground-to-air SC system on UAVs, utilizing the aerial advantage to provide favorable channels. Subsequently, we employ DM for intelligent signal processing, adaptively denoising channel interferences and optimizing received images with respect to numerical errors and perceptual loss. The results show that D-JSCC consistently exhibits superior performance across various metrics over different channel conditions.

Diffusion Model-Enabled Intelligent Channel Denoising for UAV Semantic Communication

Pengfei Ren, Jingjing Wang, Beihang University; Junhui Qian, Chongqing University; Jianrui Chen, Beihang University; Xin Zhang, Hong Kong University of Science and Technology; Chunxiao Jiang, Tsinghua University