Gaussian RateDistortionPerception Coding and Entropy-Constrained Scalar Quantization

Li Xie

doi:10.1109/TCOMM.2026.3652499

Gaussian RateDistortionPerception Coding and Entropy-Constrained Scalar Quantization

2026-01-01

1

PRE

AI

张中山 (Zhongshan Zhang)

DOI：10.1109/TCOMM.2026.3652499

Original

Original request for help

Save

Abstract

En 中文

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:

Image coding

Distortion measurement

Channel coding

Lower bound

Decoding

Distortion

Upper bound

Quantization (signal)

Source coding

Transportation

Entropy-constrained scalar quantizer

Gaussian source

Kullback-Leibler divergence

optimal transport

rate-distortion-perception coding

squared error

transportation inequality

Wasserstein distance

Gaussian RateDistortionPerception Coding and Entropy-Constrained Scalar Quantization

Abstract

Journal

Organization