Joint Source-Channel-Generation Coding: From Distortion-oriented Reconstruction to Semantic-consistent Generation

TL;DR

This paper introduces JSCGC, a new communication paradigm that uses generative models to prioritize semantic fidelity over traditional distortion metrics, leading to more realistic and perceptually aligned image transmission.

Contribution

It proposes a novel joint source-channel-generation coding framework that shifts from deterministic reconstruction to probabilistic generation, incorporating a theoretical limit on semantic inconsistency.

Findings

Significantly improves perceptual quality of transmitted images.

Outperforms traditional distortion-based JSCC methods.

Provides a theoretical bound on semantic inconsistency.

Abstract

Conventional communication systems, including both separation-based coding and AI-driven joint source-channel coding (JSCC), are largely guided by Shannon's rate-distortion theory. However, relying on generic distortion metrics fails to capture complex human visual perception, often resulting in blurred or unrealistic reconstructions. In this paper, we propose Joint Source-Channel-Generation Coding (JSCGC), a novel paradigm that shifts the focus from deterministic reconstruction to probabilistic generation. JSCGC leverages a generative model at the receiver as a generator rather than a conventional decoder to parameterize the data distribution, enabling direct maximization of mutual information under channel constraints while controlling stochastic sampling to produce outputs residing on the authentic data manifold with high fidelity. We further derive a theoretical lower bound on the maximum semantic inconsistency with given transmitted mutual information, elucidating the fundamental limits of communication in controlling the generative process. Extensive experiments on image transmission demonstrate that JSCGC substantially improves perceptual quality and semantic fidelity, significantly outperforming conventional distortion-oriented JSCC methods.