Stochastic Super-Resolution For Gaussian Textures

TL;DR

This paper introduces an efficient stochastic super-resolution method for Gaussian stationary textures, leveraging Gaussian conditional sampling and Fourier transforms to produce realistic high-resolution textures from low-resolution images.

Contribution

It presents a novel, fast algorithm for stochastic super-resolution of Gaussian textures, demonstrating practical effectiveness and improved speed over existing methods.

Findings

The method effectively generates realistic high-resolution textures.

It outperforms some state-of-the-art approaches in speed and visual quality.

Applicable specifically to stationary microtextures.

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.