Non-Stationary Texture Synthesis by Adversarial Expansion
This addresses a problem in computer graphics and vision for generating realistic textures, though it appears incremental as it builds on GANs for a specific bottleneck.
The paper tackles the challenge of synthesizing non-stationary textures, such as those with large-scale structures or spatial variations, by proposing a GAN-based method that expands texture blocks from an exemplar, demonstrating effectiveness in handling textures that existing methods cannot.
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.