AI 中文总结
研究针对经典率失真理论中失真度量不能很好捕捉感知质量等问题，提出率-失真-感知理论，通过引入感知扩展RD框架得到RDPF，介绍其编码原理、计算工具及相关结果，并概述了相关交叉领域的研究方向。
AI 中文摘要
经典率失真（RD）理论长期以来通过量化在规定失真约束下表示源所需的最小比特数，确立了有损压缩的基本极限。然而，诸如均方误差等广泛使用的失真度量常常无法捕捉感知质量或语义有效性，而这在现代学习驱动的应用中愈发重要。率-失真-感知（RDP）理论通过引入感知作为第三个基本轴扩展了RD框架，通过源信号与重构信号之间的分布相似性进行量化，从而得到率-失真-感知函数（RDPF）。本教程提供了感知感知有损压缩编码原理的结构化概述，并概述了在不同随机性假设下最近的可达性结果。然后针对离散和连续源，在包括f-散度、α-散度和基于瓦瑟斯坦的度量等广泛的感知约束族下，提出了一种统一的优化观点来计算由布劳和米凯利定义的RDPF。特别关注了诸如交替最小化方案、基于牛顿的方法和凸优化公式等计算工具，以及高斯源和完美现实主义 regime 等易于分析处理的情况。与最近强调生成架构和人工智能赋能通信系统的广泛调查不同，本教程专注于表征、计算和解释RDP极限所需的编码理论和计算机制。最后，本教程概述了信息论、神经压缩、鲁棒源编码和感知感知网络控制系统交叉领域的有前景的研究方向。
英文摘要
Classical rate-distortion (RD) theory has long established the fundamental limits of lossy compression by quantifying the minimum number of bits required to represent a source under a prescribed distortion constraint. However, widely used distortion measures such as mean-squared error often fail to capture perceptual quality or semantic validity, which are increasingly central in modern learning-driven applications. Rate-distortion-perception (RDP) theory extends the RD framework by introducing perception as a third fundamental axis, quantified via distributional similarity between the source and reconstructed signals, leading to the rate-distortion-perception function (RDPF). This tutorial provides a structured overview of the coding principles underlying perception-aware lossy compression and surveys recent achievability results under different randomness assumptions. It then presents a unifying optimization viewpoint for computing the RDPF as defined by Blau and Michaeli, for both discrete and continuous sources under broad families of perceptual constraints, including f-divergences, alpha-divergences, and Wasserstein-based metrics. Special attention is given to computational tools such as alternating minimization schemes, Newton-based methods, and convex optimization formulations, as well as to analytically tractable cases such as Gaussian sources and the perfect-realism regime. Unlike recent broad surveys that emphasize generative architectures and AI-empowered communication systems, this tutorial focuses on the coding-theoretic and computational machinery needed to characterize, compute, and interpret the RDP limits. Finally, the tutorial outlines promising research directions at the intersection of information theory, neural compression, robust source coding, and perception-aware networked control systems.
Comments20 pages, 10 figures, IEEE BITS
