Low-Rate, Low-Distortion Compression with Wasserstein Distortion
Author:
Yang Qiu, Aaron B. Wagner
Keyword:
Computer Science, Information Theory, Information Theory (cs.IT)
journal:
--
date:
2024-01-30 00:00:00
Abstract
Wasserstein distortion is a one-parameter family of distortion measures that was recently proposed to unify fidelity and realism constraints. After establishing continuity results for Wasserstein in the extreme cases of pure fidelity and pure realism, we prove the first coding theorems for compression under Wasserstein distortion focusing on the regime in which both the rate and the distortion are small.