Macrocanonical Models for Texture Synthesis
Langue
en
Communication dans un congrès
Ce document a été publié dans
Scale Space and Variational Methods in Computer Vision. SSVM 2019, 2019-06-30, Hofgeismar. vol. 11603
Résumé en anglais
In this article we consider macrocanonical models for texture synthesis. In these models samples are generated given an input texture image and a set of features which should be matched in expectation. It is known that if ...Lire la suite >
In this article we consider macrocanonical models for texture synthesis. In these models samples are generated given an input texture image and a set of features which should be matched in expectation. It is known that if the images are quantized, macrocanonical models are given by Gibbs measures, using the maximum entropy principle. We study conditions under which this result extends to real-valued images. If these conditions hold, finding a macrocanonical model amounts to minimizing a convex function and sampling from an associated Gibbs measure. We analyze an algorithm which alternates between sampling and minimizing. We present experiments with neural network features and study the drawbacks and advantages of using this sampling scheme.< Réduire
Mots clés en anglais
Texture synthesis
Gibbs measure
Monte Carlo methods
Langevin algorithms
Neural networks
Origine
Importé de halUnités de recherche