TileGAN: Synthesis of Large-Scale Non-Homogeneous Textures

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.

Code is available at http://github.com/afruehstueck/tileGAN

References in corpus (1)

• GANosaic: Mosaic Creation with Generative Texture Manifolds

Cited by in corpus (5)

• Guided Fine-Tuning for Large-Scale Material Transfer
• GramGAN: Deep 3D Texture Synthesis From 2D Exemplars
• Transposer: Universal Texture Synthesis Using Feature Maps as Transposed Convolution Filter
• Translate the Facial Regions You Like Using Region-Wise Normalization
• Deep Tiling: Texture Tile Synthesis Using a Deep Learning Approach