The Distortion-Perception Tradeoff in Finite Channels with Arbitrary Distortion Measures
Keywords: distortion-perception tradeoff, perceptual quality, discrete channels, estimation theory, signal reconstruction
TL;DR: We study the distortion-perception tradeoff over finite-alphabet channels.
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.
We study this distortion-perception (DP) tradeoff over finite-alphabet channels, for the Wasserstein-$1$ distance as the perception index, and an arbitrary distortion matrix. We show that computing the DP function and the optimal
reconstructions is equivalent to solving a set of linear programming problems. We prove that the DP curve is a piecewise linear function of the perception index, and derive a closed-form expression for the case of binary sources.
Submission Number: 21
Loading