Texture Mixing by Interpolating Deep Statistics via Gaussian Models

2Citations
Citations of this article
15Readers
Mendeley users who have this article in their library.

This article is free to access.

Abstract

Recently, enthusiastic studies have devoted to texture synthesis using deep neural networks, because these networks excel at handling complex patterns in images. In these models, second-order statistics, such as Gram matrix, are used to describe textures. Although these models have achieved promising results, the structure of their parametric space is still unclear. Consequently, it is difficult to use them to mix textures. This paper addresses the texture mixing problem by using a Gaussian scheme to interpolate deep statistics computed from deep neural networks. More precisely, we first reveal that the statistics used in existing deep models can be unified using a stationary Gaussian scheme. We then present a novel algorithm to mix these statistics by interpolating between Gaussian models using optimal transport. We further apply our scheme to Neural Style Transfer, where we can create mixed styles. The experiments demonstrate that our method outperforms a number of baselines. Because all the computations are implemented in closed forms, our mixing algorithm adds only negligible time to the original texture synthesis procedure.

Cite

CITATION STYLE

APA

Xue, Z., & Wang, Z. (2020). Texture Mixing by Interpolating Deep Statistics via Gaussian Models. IEEE Access, 8, 60747–60758. https://doi.org/10.1109/ACCESS.2020.2981410

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free