Cours/Séminaire
Notice
Lieu de réalisation
France
Langue :
Anglais
Crédits
Photios A. Stavrou (Intervention)
Conditions d'utilisation
Droit commun de la propriété intellectuelle
DOI : 10.60527/qp7p-ew76
Citer cette ressource :
Photios A. Stavrou. FOUNDS. (2024, 1 mars). FOUNDS Seminar Series Talk 06 - Computation of the Rate-Distortion-Perception Function. [Vidéo]. Canal-U. https://doi.org/10.60527/qp7p-ew76. (Consultée le 3 novembre 2026)
FOUNDS
FOUNDS
S'abonner
Contacter

FOUNDS Seminar Series Talk 06 - Computation of the Rate-Distortion-Perception Function

Réalisation : 1 mars 2024 - Mise en ligne : 3 mars 2024
  • document 1 document 2 document 3
  • niveau 1 niveau 2 niveau 3
Descriptif

Talk Abstract: In this talk, we study methods for the computation of a generalization of the rate-distortion function called the rate-distortion-perception function (RDPF). This generalization to the rate-distortion problem was defined by the computer vision and machine learning community in recent years, to give a mathematical interpretation to the observation that “low distortion” is not a synonym for “high perceptual quality”, and, from an optimization perspective, there is a tradeoff between the distortion and the perception. The RDPF is also a relevant semantic-based metric in compression. For discrete sources, with single-letter distortion and a perception constraint that belongs to the family of f-divergences, we compute the RDPF by proposing an approximate alternating minimization approach a la Blahut-Arimoto algorithm that converges to a globally optimal point. For scalar Gaussian sources with squared error distortion and a perception constraint that can be either the KL divergence, the squared Wasserstein distance, the squared Hellinger distance, or the geometric Jensen-Shannon divergence, we derive closed-form expressions under the assumption of jointly Gaussian processes. Our closed-form solutions are also supported by their corresponding test-channel forward realizations, the first of their kind. For vector Gaussian sources, we propose a generic alternating minimization algorithm using a block-coordinated descent method that can optimally compute the vector Gaussian RDPF. For the extreme case of the perfect-realism vector Gaussian RDPF, that is to say, when the Gaussian distribution of the source and the reconstruction are constrained to be the same, we derive in closed-form solution a new optimal adaptive reverse-water- filling solution. We corroborate our findings with various simulation studies.

Intervention / Responsable scientifique
Thème
Disciplines :
Documentation

Sur le même thème