研究人员引入了联合信源-信道-生成编码（JSCGC），这是一种利用接收端生成模型的新型通信范式。该方法超越了传统的率失真理论，将通信重新定义为受控生成，旨在在感知约束下最大化互信息，而不是仅仅最小化失真。实验表明，JSCGC在图像传输中提高了基于特征、语义和分布的质量，并表现出语义不一致作为一种独特的错误特征。 AI
影响 引入了一种新的生成通信范式，有望提高数据传输的质量和效率。
排序理由 这是一篇描述新技术的 ist 研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.12858v1 Announce Type: cross Abstract: 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 distortio…
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 pe…