High resolution neural texture synthesis with long range constraints

TL;DR

This paper introduces a multi-resolution neural texture synthesis framework with long-range constraints, significantly improving the reproduction of large-scale, high-resolution textures with regular structures.

Contribution

The authors propose a simple multi-resolution framework combined with statistical constraints, enhancing neural texture synthesis for high-resolution and regular textures.

Findings

Multi-scale scheme improves high-resolution texture synthesis.

Combining constraints enhances regular texture reproduction.

Experimental results outperform alternative methods.

Abstract

The field of texture synthesis has witnessed important progresses over the last years, most notably through the use of Convolutional Neural Networks. However, neural synthesis methods still struggle to reproduce large scale structures, especially with high resolution textures. To address this issue, we first introduce a simple multi-resolution framework that efficiently accounts for long-range dependency. Then, we show that additional statistical constraints further improve the reproduction of textures with strong regularity. This can be achieved by constraining both the Gram matrices of a neural network and the power spectrum of the image. Alternatively one may constrain only the autocorrelation of the features of the network and drop the Gram matrices constraints. In an experimental part, the proposed methods are then extensively tested and compared to alternative approaches, both in an unsupervised way and through a user study. Experiments show the interest of the multi-scale scheme for high resolution textures and the interest of combining it with additional constraints for regular textures.