Gaussian Rate–Distortion–Perception Coding and Entropy-Constrained Scalar Quantization
- 12 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 74 (00906778) , 3298-3312
Abstract
This paper investigates the tightness of existing bounds on the quadratic Gaussian distortion-rate-perception functions with limited common randomness and the i.i.d. output constraint, under perception measures based on the Kullback–Leibler divergence and the squared Wasserstein-2 distance. For the squared Wasserstein-2 distance-based perception measure, we improve the best-known lower bound by introducing a tunable parameter. Moreover, via the connection between rate-distortion-perception coding and entropy-constrained scalar quantization, it is revealed that all existing bounds, including the improved one, are generally not tight in the weak perception constraint regime. Our findings shed light on the information-theoretic performance limits of rate-distortion-perception coding and offer guidelines for developing practical schemes.Keywords
This publication has 27 references indexed in Scilit:
- Source-Channel Separation Theorems for Distortion Perception Coding2025
- Information Theory2024
- Copula-Based Estimation of Continuous Sources for a Class of Constrained Rate-Distortion Functions2024
- The Rate-Distortion-Perception Trade-off: the Role of Private Randomness2024
- Characterization of the Distortion-Perception Tradeoff for Finite Channels with Arbitrary Metrics2024
- An Invitation to Statistics in Wasserstein Space2020
- The Perception-Distortion Tradeoff2018
- Optimal Transport2009
- On the structure of optimal entropy-constrained scalar quantizersIEEE Transactions on Information Theory, 2002
- Elements of Information Theory2001