Rate-Distortion-Perception Controllable Joint Source-Channel Coding for High-Fidelity Generative Communications

TL;DR

This paper introduces a novel joint source-channel coding framework that optimizes for rate, distortion, and perception, enabling high-fidelity, realistic image transmission with customizable realism and content prioritization.

Contribution

It proposes a rate-distortion-perception optimized JSCC framework with plug-in GANs, a distortion-perception controllable model, and a content-controllable transmission scheme for perceptually pleasing images.

Findings

Outperforms state-of-the-art image transmission systems.

Provides customizable perception and realism control.

Efficiently transmits attention-focused image regions.

Abstract

End-to-end image transmission has recently become a crucial trend in intelligent wireless communications, driven by the increasing demand for high bandwidth efficiency. However, existing methods primarily optimize the trade-off between bandwidth cost and objective distortion, often failing to deliver visually pleasing results aligned with human perception. In this paper, we propose a novel rate-distortion-perception (RDP) jointly optimized joint source-channel coding (JSCC) framework to enhance perception quality in human communications. Our RDP-JSCC framework integrates a flexible plug-in conditional Generative Adversarial Networks (GANs) to provide detailed and realistic image reconstructions at the receiver, overcoming the limitations of traditional rate-distortion optimized solutions that typically produce blurry or poorly textured images. Based on this framework, we introduce a distortion-perception controllable transmission (DPCT) model, which addresses the variation in the perception-distortion trade-off. DPCT uses a lightweight spatial realism embedding module (SREM) to condition the generator on a realism map, enabling the customization of appearance realism for each image region at the receiver from a single transmission. Furthermore, for scenarios with scarce bandwidth, we propose an interest-oriented content-controllable transmission (CCT) model. CCT prioritizes the transmission of regions that attract user attention and generates other regions from an instance label map, ensuring both content consistency and appearance realism for all regions while proportionally reducing channel bandwidth costs. Comprehensive experiments demonstrate the superiority of our RDP-optimized image transmission framework over state-of-the-art engineered image transmission systems and advanced perceptual methods.