Semantic-Aware Visual Information Transmission With Key Information Extraction Over Wireless Networks

TL;DR

This paper introduces a semantic-aware deep joint source-channel coding framework for 6G wireless image transmission, utilizing AI-driven key information extraction and adaptive background synthesis to improve efficiency and robustness.

Contribution

It presents a novel AI-native JSCC approach that integrates semantic-aware features and adaptive background synthesis for resource-constrained 6G networks.

Findings

Significant PSNR improvements over traditional JSCC under low-SNR conditions

Effective reduction of data payloads while maintaining visual quality

Enhanced robustness and adaptability in dynamic wireless environments

Abstract

The advent of 6G networks demands unprecedented levels of intelligence, adaptability, and efficiency to address challenges such as ultra-high-speed data transmission, ultra-low latency, and massive connectivity in dynamic environments. Traditional wireless image transmission frameworks, reliant on static configurations and isolated source-channel coding, struggle to balance computational efficiency, robustness, and quality under fluctuating channel conditions. To bridge this gap, this paper proposes an AI-native deep joint source-channel coding (JSCC) framework tailored for resource-constrained 6G networks. Our approach integrates key information extraction and adaptive background synthesis to enable intelligent, semantic-aware transmission. Leveraging AI-driven tools, Mediapipe for human pose detection and Rembg for background removal, the model dynamically isolates foreground features and matches backgrounds from a pre-trained library, reducing data payloads while preserving visual fidelity. Experimental results demonstrate significant improvements in peak signal-to-noise ratio (PSNR) compared with traditional JSCC method, especially under low-SNR conditions. This approach offers a practical solution for multimedia services in resource-constrained mobile communications.