EUVIMEDEUVIMED entdecken
Crossref

Rate-Distortion-Perception Trade-Off With Strong Realism Constraints: Role of Side Information and Common Randomness

Yassine Hamdi, Aaron B. Wagner, Deniz Gunduz

IEEE Transactions on Information Theory · 2026-09 · 72 (9) · 6401-6421

DOI: 10.1109/tit.2026.3702694 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Information Theory, 2026-09. Verfasst von Yassine Hamdi und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: European Union’s Horizon 2020 Marie Skłodowska Curie Innovative Training Network Greenedge, UKRI, SNS JU project 6G-GOALS.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In image compression, with recent advances in generative modeling, existence of a trade-off between rate and perceptual quality has been brought to light, where perceptual quality is measured by the closeness of the output and source distributions. We consider the compression of a memoryless source sequence $X^{n}=(X_{1}, \ldots, X_{n})$ in the presence of memoryless side information $Z^{n}=(Z_{1}, \ldots, Z_{n})$ , originally studied by Wyner and Ziv, but elucidate the impact of a strong perfect realism constraint, which requires the joint distribution of output symbols $Y^{n} = (Y_{1},\ldots,Y_{n})$ to match the distribution of the source sequence. We consider two cases: when $Z^{n}$ is available only at the decoder, or at both the encoder and decoder, and characterize the information theoretic limits in both scenarios. Previous works show the superiority of randomized codes under strong perceptual quality constraints. When $Z^{n}$ is available at both terminals, we characterize its dual role, as a source of common randomness, and as a second look on the source for the receiver. We also study different notions of strong perfect realism, which we call marginal realism , joint realism and near-perfect realism . We derive explicit solutions when $X$ and $Z$ are jointly Gaussian under the squared error distortion measure. In traditional lossy compression, having $Z$ only at the decoder imposes no rate penalty in the Gaussian scenario. We show that, when strong perfect realism constraints are imposed this holds only when sufficient common randomness is available.

Förderung

  • European Union’s Horizon 2020 Marie Skłodowska Curie Innovative Training Network Greenedge
  • UKRI
  • SNS JU project 6G-GOALS
  • US National Science Foundation

Zitieren

APA

Hamdi, Y., Wagner, A. B., & Gunduz, D. (2026). Rate-Distortion-Perception Trade-Off With Strong Realism Constraints: Role of Side Information and Common Randomness. IEEE Transactions on Information Theory, 72(9), 6401-6421. https://doi.org/10.1109/tit.2026.3702694

Vancouver

Hamdi Y, Wagner AB, Gunduz D. Rate-Distortion-Perception Trade-Off With Strong Realism Constraints: Role of Side Information and Common Randomness. IEEE Transactions on Information Theory. 2026;72(9):6401-6421. doi:10.1109/tit.2026.3702694

BibTeX
@article{Hamdi2026,
  author = {Hamdi, Yassine and Wagner, Aaron B. and Gunduz, Deniz},
  title = {Rate-Distortion-Perception Trade-Off With Strong Realism Constraints: Role of Side Information and Common Randomness},
  journal = {IEEE Transactions on Information Theory},
  year = {2026},
  volume = {72},
  number = {9},
  pages = {6401--6421},
  doi = {10.1109/tit.2026.3702694}
}
Kostenlos starten →