🤖 AI Summary
For latency-sensitive semantic communication, this paper addresses the speed–quality trade-off in information transmission under uncertain channel conditions by proposing a novel rateless joint source-channel coding (JSCC) framework. Methodologically, it introduces semantic-level reconstruction objectives into the rateless coding architecture for the first time, establishing a dual-objective optimization paradigm balancing rate-distortion and perceptual fidelity. It further designs a variable-rate semantic-robust transmission mechanism integrating a generative decoder, dithered quantization, and multi-granularity (pixel- and semantic-level) reconstruction losses. Experimental results demonstrate continuous, automatic rate adaptation under dynamic channel conditions. The approach achieves a 23% reduction in LPIPS—indicating significantly improved perceptual fidelity—while maintaining competitive PSNR performance, and boosts downstream semantic task accuracy by 12.7% over conventional JSCC methods.
📝 Abstract
We consider the problem of joint source-channel coding for semantic communication from a rateless perspective, the purpose of which is to settle the balance between reliability (distortion/perception) and effectiveness (rate) of transmission over uncertain channels. In particular, we propose a more general communication objective that minimizes the perceptual distance by incorporating a semantic-level reconstruction objective in addition to the conventional pixel-level reconstruction objective. Based on the proposed objective, we then propose a novel JSCC coding scheme called rateless stochastic coding (RSC) by introducing a generative decoder and dithered quantization. The coding scheme enables reconstruction based on both distortion and perception metrics through rateless transmission. Extensive experiments demonstrate that the proposed RSC can achieve variable rates of transmission maintaining an excellent trade-off between distortion and perception.