Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hamdi, Yassine, Wagner, Aaron B., Gündüz, Deniz
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.15255
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917092278665216
author Hamdi, Yassine
Wagner, Aaron B.
Gündüz, Deniz
author_facet Hamdi, Yassine
Wagner, Aaron B.
Gündüz, Deniz
contents Realism constraints (or constraints on perceptual quality) have received considerable recent attention within the context of lossy compression, particularly of images. Theoretical studies of lossy compression indicate that high-rate common randomness between the compressor and the decompressor is a valuable resource for achieving realism. On the other hand, the utility of significant amounts of common randomness has not been noted in practice. We offer an explanation for this discrepancy by considering a realism constraint that requires satisfying a universal critic that inspects realizations of individual compressed reconstructions, or batches thereof. We characterize the optimal rate-distortion trade-off under such a realism constraint, and show that it is asymptotically achievable without any common randomness, unless the batch size is impractically large.
format Preprint
id arxiv_https___arxiv_org_abs_2511_15255
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle The Rate-Distortion-Perception Trade-Off with Algorithmic Realism
Hamdi, Yassine
Wagner, Aaron B.
Gündüz, Deniz
Information Theory
Realism constraints (or constraints on perceptual quality) have received considerable recent attention within the context of lossy compression, particularly of images. Theoretical studies of lossy compression indicate that high-rate common randomness between the compressor and the decompressor is a valuable resource for achieving realism. On the other hand, the utility of significant amounts of common randomness has not been noted in practice. We offer an explanation for this discrepancy by considering a realism constraint that requires satisfying a universal critic that inspects realizations of individual compressed reconstructions, or batches thereof. We characterize the optimal rate-distortion trade-off under such a realism constraint, and show that it is asymptotically achievable without any common randomness, unless the batch size is impractically large.
title The Rate-Distortion-Perception Trade-Off with Algorithmic Realism
topic Information Theory
url https://arxiv.org/abs/2511.15255