2606.12858v1 Jun 11, 2026 cs.IT

JSCGC: Joint Source-Channel-Generation Coding for Wireless Generative Communications

Li Song
Li Song
Citations: 113
h-index: 6
Zhiyong Chen
Zhiyong Chen
Citations: 329
h-index: 9
Meixia Tao
Meixia Tao
Citations: 512
h-index: 10
Tong Wu
Tong Wu
Citations: 211
h-index: 6
Guo Lu
Guo Lu
Citations: 156
h-index: 8
Feng Yang
Feng Yang
Citations: 8
h-index: 1
Wenjun Zhang
Wenjun Zhang
Citations: 12
h-index: 2

Conventional communication systems, including both separation-based coding and learning-based joint source-channel coding (JSCC), are typically designed under 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 generative communication paradigm that replaces the conventional decoder with a generative model at the receiver. The received signal is treated as a condition that controls the sampling process into the learned conditional distribution, reformulating communication from deterministic reconstruction for distortion minimization to controlled generation for mutual information maximization under perceptual constraints. Based on this formulation, we develop a unified joint training and efficient stochastic sampling framework, and provide theoretical analysis of its effectiveness in both learning and inference stages. Extensive experiments on latent-space image transmission demonstrate that the JSCGC consistently improves feature-based, semantic-level, and distributional quality across diverse channel conditions, while exhibiting a distinct error behavior characterized by semantic inconsistency rather than distortion.

0 Citations
0 Influential
5 Altmetric
25.0 Score
Original PDF

No Analysis Report Yet

This paper hasn't been analyzed by Gemini yet.

Log in to request an AI analysis.

댓글

댓글을 작성하려면 로그인하세요.

아직 댓글이 없습니다. 첫 번째 댓글을 남겨보세요!