A Generative Model for Texture Synthesis based on Optimal Transport between Feature Distributions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Houdard, Antoine, Leclaire, Arthur, Papadakis, Nicolas, Rabin, Julien
Format: Preprint
Published: 2020
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929300702232576
author Houdard, Antoine
Leclaire, Arthur
Papadakis, Nicolas
Rabin, Julien
author_facet Houdard, Antoine
Leclaire, Arthur
Papadakis, Nicolas
Rabin, Julien
contents We propose GOTEX, a general framework for texture synthesis by optimization that constrains the statistical distribution of local features. While our model encompasses several existing texture models, we focus on the case where the comparison between feature distributions relies on optimal transport distances. We show that the semi-dual formulation of optimal transport allows to control the distribution of various possible features, even if these features live in a high-dimensional space. We then study the resulting minimax optimization problem, which corresponds to a Wasserstein generative model, for which the inner concave maximization problem can be solved with standard stochastic gradient methods. The alternate optimization algorithm is shown to be versatile in terms of applications, features and architecture; in particular it allows to produce high-quality synthesized textures with different sets of features. We analyze the results obtained by constraining the distribution of patches or the distribution of responses to a pre-learned VGG neural network. We show that the patch representation can retrieve the desired textural aspect in a more precise manner. We also provide a detailed comparison with state-of-the-art texture synthesis methods. The GOTEX model based on patch features is also adapted to texture inpainting and texture interpolation. Finally, we show how to use our framework to learn a feed-forward neural network that can synthesize on-the-fly new textures of arbitrary size in a very fast manner. Experimental results and comparisons with the mainstream methods from the literature illustrate the relevance of the generative models learned with GOTEX.
format Preprint
id arxiv_https___arxiv_org_abs_2007_03408
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle A Generative Model for Texture Synthesis based on Optimal Transport between Feature Distributions
Houdard, Antoine
Leclaire, Arthur
Papadakis, Nicolas
Rabin, Julien
Computer Vision and Pattern Recognition
Machine Learning
We propose GOTEX, a general framework for texture synthesis by optimization that constrains the statistical distribution of local features. While our model encompasses several existing texture models, we focus on the case where the comparison between feature distributions relies on optimal transport distances. We show that the semi-dual formulation of optimal transport allows to control the distribution of various possible features, even if these features live in a high-dimensional space. We then study the resulting minimax optimization problem, which corresponds to a Wasserstein generative model, for which the inner concave maximization problem can be solved with standard stochastic gradient methods. The alternate optimization algorithm is shown to be versatile in terms of applications, features and architecture; in particular it allows to produce high-quality synthesized textures with different sets of features. We analyze the results obtained by constraining the distribution of patches or the distribution of responses to a pre-learned VGG neural network. We show that the patch representation can retrieve the desired textural aspect in a more precise manner. We also provide a detailed comparison with state-of-the-art texture synthesis methods. The GOTEX model based on patch features is also adapted to texture inpainting and texture interpolation. Finally, we show how to use our framework to learn a feed-forward neural network that can synthesize on-the-fly new textures of arbitrary size in a very fast manner. Experimental results and comparisons with the mainstream methods from the literature illustrate the relevance of the generative models learned with GOTEX.
title A Generative Model for Texture Synthesis based on Optimal Transport between Feature Distributions
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2007.03408