Hybrid Semantic-Complementary Transmission for High-Fidelity Image Reconstruction

TL;DR

This paper introduces a hybrid semantic communication framework that combines semantic representations with complementary residual information to significantly improve high-fidelity image reconstruction over neural network-based systems.

Contribution

The paper proposes a novel hybrid semantic communication framework that supplements semantic representations with adjustable residual information, enhancing image reconstruction fidelity.

Findings

HSC reduces mean squared error compared to baseline SC.

The residual representation load can be flexibly adjusted for optimal fidelity.

Closed-form expression for reconstruction error and optimal residual transmission is derived.

Abstract

Recent advances in semantic communication (SC) have introduced neural network (NN)-based transceivers that convey semantic representation (SR) of signals such as images. However, these NNs are trained over diverse image distributions and thus often fail to reconstruct fine-grained image-specific details. To overcome this limited reconstruction fidelity, we propose an extended SC framework, hybrid semantic communication (HSC), which supplements SR with complementary representation (CR) capturing residual image-specific information. The CR is constructed at the transmitter, and is combined with the actual SC outcome at the receiver to yield a high-fidelity recomposed image. While the transmission load of SR is fixed due to its NN-based structure, the load of CR can be flexibly adjusted to achieve a desirable fidelity. This controllability directly influences the final reconstruction error, for which we derive a closed-form expression and the corresponding optimal CR. Simulation results demonstrate that HSC substantially reduces MSE compared to the baseline SC without CR transmission across various channels and NN architectures.