Generative AI-Enhanced Robust Semantic Communication Architecture for UAV Image Transmission

Abstract

Unmanned aerial vehicle (UAV) wireless image transmission has gained widespread application across various fields due to its flexibility, yet it faces critical challenges such as resource constraints and degradation of reconstruction quality caused by harsh channel conditions. To address these issues, we designed a lightweight semantic communication backbone network that substantially reduces the computational and storage overhead of UAVs through codebook assistance and efficient encoder-decoder design. On this basis, to tackle severe image degradation under adverse channel conditions, we introduced a generative artificial intelligence-based (GAI) enhancement module. Specifically, we developed a semantic refinement network (SRN) that employs an innovative signal-to-noise ratio (SNR) adaptive feature-wise linear modulation (FiLM) layer to dynamically adjust its refinement strategy based on real-time channel quality, fundamentally transforming the image reconstruction paradigm from traditional signal recovery to conditional content generation. Extensive experimental results demonstrate that our proposed framework significantly outperforms the current state-of-the-art method under extreme channel conditions, highlighting its great potential for achieving robust UAV image transmission in challenging operational environments.