Non-stationary texture synthesis by adversarial expansion

TLDR

The real world contains many non‑stationary textures, such as large‑scale structures and spatially variant patterns, which existing example‑based synthesis methods struggle to reproduce. This work introduces a new example‑based approach for synthesizing non‑stationary textures. The method trains a generative adversarial network to double the spatial extent of texture blocks, enabling a fully convolutional generator to expand the entire exemplar and any sub‑blocks. Experiments show that this simple technique captures large‑scale structures and other non‑stationary attributes, outperforming prior methods on challenging textures.

Abstract

The real world exhibits an abundance of non-stationary textures. Examples include textures with large scale structures, as well as spatially variant and inhomogeneous textures. While existing example-based texture synthesis methods can cope well with stationary textures, non-stationary textures still pose a considerable challenge, which remains unresolved. In this paper, we propose a new approach for example-based non-stationary texture synthesis. Our approach uses a generative adversarial network (GAN), trained to double the spatial extent of texture blocks extracted from a specific texture exemplar. Once trained, the fully convolutional generator is able to expand the size of the entire exemplar, as well as of any of its sub-blocks. We demonstrate that this conceptually simple approach is highly effective for capturing large scale structures, as well as other non-stationary attributes of the input exemplar. As a result, it can cope with challenging textures, which, to our knowledge, no other existing method can handle.