Local Padding in Patch-Based GANs for Seamless Infinite-Sized Texture Synthesis
This work solves the problem of generating high-quality, diverse large-scale textures for applications like computer graphics and image processing, representing an incremental improvement over existing GAN-based texture models.
The paper tackles the problem of generating seamless infinite-sized textures using GANs by addressing issues with zero-padding that degrade image quality and limit diversity; it proposes local padding to share border features between patches, resulting in significant advancements in quality and diversity for texture synthesis and elimination of tiling artifacts in super-resolution models.
Texture models based on Generative Adversarial Networks (GANs) use zero-padding to implicitly encode positional information of the image features. However, when extending the spatial input to generate images at large sizes, zero-padding can often lead to degradation in image quality due to the incorrect positional information at the center of the image. Moreover, zero-padding can limit the diversity within the generated large images. In this paper, we propose a novel approach for generating stochastic texture images at large arbitrary sizes using GANs based on patch-by-patch generation. Instead of zero-padding, the model uses \textit{local padding} in the generator that shares border features between the generated patches; providing positional context and ensuring consistency at the boundaries. The proposed models are trainable on a single texture image and have a constant GPU scalability with respect to the output image size, and hence can generate images of infinite sizes. We show in the experiments that our method has a significant advancement beyond existing GANs-based texture models in terms of the quality and diversity of the generated textures. Furthermore, the implementation of local padding in the state-of-the-art super-resolution models effectively eliminates tiling artifacts enabling large-scale super-resolution. Our code is available at \url{https://github.com/ai4netzero/Infinite_Texture_GANs}.