Stochastic Super-Resolution For Gaussian Textures

2023/03/03 by Emile Pierret, Pierret, Emile, Bruno Galerne +1
Computer Science · Engineering · #Advanced Image Processing Techniques #FOS: Electrical engineering #Image Processing Techniques and Applications #Image and Video Processing (eess.IV) #Photoacoustic and Ultrasonic Imaging #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2303.01831

openalex publication_date 2023/03/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Generative Modeling by Estimating Gradients of the Data Distribution
• Denoising Diffusion Probabilistic Models
• The basins of attraction of the global minimizers of non-convex inverse\n problems with low-dimensional models in infinite dimension
• Generative Adversarial Nets

Related

• Stochastic super-resolution for Gaussian microtextures
• Fast Single Image Super-Resolution
• Image Super-Resolution via Iterative Refinement
• Diverse super-resolution with pretrained deep hiererarchical VAEs
• Improved Stochastic Texture Filtering Through Sample Reuse