# TileGAN: Synthesis of Large-Scale Non-Homogeneous Textures

## TL;DR

TileGAN introduces a method to generate large-scale, high-resolution, non-homogeneous textures by combining GAN outputs and providing artistic control, enabling the synthesis of textures up to hundreds of megapixels.

## Contribution

The paper presents a novel approach to scale up GAN-based texture synthesis for large, non-homogeneous textures with boundary artifact reduction and user-guided artistic control.

## Key findings

- Generated textures up to hundreds of megapixels.
- Effective boundary artifact minimization.
- User interface for artistic control.

## Abstract

We tackle the problem of texture synthesis in the setting where many input images are given and a large-scale output is required. We build on recent generative adversarial networks and propose two extensions in this paper. First, we propose an algorithm to combine outputs of GANs trained on a smaller resolution to produce a large-scale plausible texture map with virtually no boundary artifacts. Second, we propose a user interface to enable artistic control. Our quantitative and qualitative results showcase the generation of synthesized high-resolution maps consisting of up to hundreds of megapixels as a case in point.