Characterization of the Distortion-Perception Tradeoff for Finite Channels with Arbitrary Metrics
Abstract
Whenever inspected by humans, reconstructed signals should not be distinguished from real ones. Typically, such a high perceptual quality comes at the price of high reconstruction error, and vice versa. We study this distortion-perception (DP) tradeoff over finite-alphabet channels, for the Wasserstein- distance induced by a general metric as the perception index, and an arbitrary distortion matrix. Under this setting, we show that computing the DP function and the optimal reconstructions is equivalent to solving a set of linear programming problems. We provide a structural characterization of the DP tradeoff, where the DP function is piecewise linear in the perception index. We further derive a closed-form expression for the case of binary sources.
Keywords
Cite
@article{arxiv.2402.02265,
title = {Characterization of the Distortion-Perception Tradeoff for Finite Channels with Arbitrary Metrics},
author = {Dror Freirich and Nir Weinberger and Ron Meir},
journal= {arXiv preprint arXiv:2402.02265},
year = {2024}
}