信号处理2025，Vol.41Issue(10)：1636-1646,11.DOI:10.12466/xhcl.2025.10.004
基于潜空间残差去噪的视频语义通信
Latent Space Residual Denoising for Video Semantic Communication
摘要
Abstract
With the proliferation of multimedia applications,visual data,such as video has come to dominate network traffic,thereby imposing increasingly stringent requirements on high-reliability and low-latency data transmission.Con-ventional separate-source and channel-coding schemes face performance bottlenecks in dynamic channel environments.As a novel communication paradigm,semantic communication improves transmission efficiency and robustness by ex-tracting and transmitting semantic information from the source.However,existing latent-space denoising methods in vi-sual semantic communication usually suffer from high computational complexity and insufficient semantic fidelity.To address these challenges,this paper proposes a video semantic communication framework based on latent-space residual denoising.The framework employs a Swin Transformer-based joint source-channel codec,and incorporates an iterative semantic denoiser designed by residual learning and similarity-based learning.The residual mapping directly predicts and removes channel noise,thereby significantly improving the denoising efficiency.Additionally,a signal-to-noise ra-tio(SNR)-driven similarity score is introduced as a conditional input to dynamically adjust the denoising intensity,and an adaptive denoising-step strategy is employed to balance performance and latency.Simulation results demonstrate that the proposed method effectively suppresses noise over additive white Gaussian noise(AWGN)channels.Moreover,it can outperform conventional separate coding and end-to-end semantic communication schemes across various distortion and perceptual video metrics,particularly under high-noise conditions.Furthermore,the proposed SNR-driven similar-ity score initialization achieves close approximation to the empirical distribution,as validated by Monte Carlo simulations.关键词
语义通信/视频传输/残差学习/余弦相似度/信道去噪Key words
semantic communication/video transmission/residual learning/cosine similarity/channel denoising分类
信息技术与安全科学引用本文复制引用
许铭楷,吴泳澎,张文军..基于潜空间残差去噪的视频语义通信[J].信号处理,2025,41(10):1636-1646,11.基金项目
国家重点研发计划(2022YFB2902100) （2022YFB2902100）
中央高校基本科研业务费专项资金项目 （）
长三角基础研究联合基金(BK20244006) （BK20244006）
高等学校学科创新引智计划(BP0719010) （BP0719010）
上海市自然科学基金项目(22DZ2229005) National Key Research and Development Program of China(2022YFB2902100) （22DZ2229005）
Fundamental Research Funds for the Central Universities （）
Yangtze River Delta Science and Technology Innovation Community Joint Research(Basic Research)Project(BK20244006) （Basic Research）
Program of Introducing Talents of Discipline to Universities(BP0719010) （BP0719010）
Natural Science Foundation of Shanghai(22DZ2229005) （22DZ2229005）
