Stochastic Super-Resolution For Gaussian Textures - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year : 2023

Stochastic Super-Resolution For Gaussian Textures

Super-résolution stochastique pour les textures Gaussiennes

Abstract

Super-resolution (SR) is an ill-posed inverse problem which consists in proposing high-resolution images consistent with a given low-resolution one. While most SR algorithms are deterministic, stochastic SR deals with designing a stochastic sampler generating any realistic SR solution. The goal of this paper is to show that stochastic SR is a well-posed and solvable problem when restricting to Gaussian stationary textures. Using Gaussian conditional sampling and exploiting the stationarity assumption, we propose an efficient algorithm based on fast Fourier transform. We also demonstrate the practical relevance of the approach for SR with a reference image. Although limited to stationary microtextures, our approach compares favorably in terms of speed and visual quality to some state of the art methods designed for a larger class of images.
Fichier principal
Vignette du fichier
2023043951.pdf (4.09 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03863009 , version 1 (21-11-2022)
hal-03863009 , version 2 (02-03-2023)

Identifiers

  • HAL Id : hal-03863009 , version 2

Cite

Émile Pierret, Bruno Galerne. Stochastic Super-Resolution For Gaussian Textures. 2023. ⟨hal-03863009v2⟩
124 View
50 Download

Share

Gmail Facebook X LinkedIn More