GRAICVApr 29, 2019

TileGAN: Synthesis of Large-Scale Non-Homogeneous Textures

arXiv:1904.12795v143 citations
Originality Incremental advance
AI Analysis

This work addresses texture synthesis for applications like computer graphics and digital art, offering a method to create large-scale outputs with artistic control, though it is incremental as it builds on existing GAN frameworks.

The paper tackled the problem of generating large-scale non-homogeneous textures from multiple input images, achieving synthesis of high-resolution maps up to hundreds of megapixels with minimal boundary artifacts.

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 Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes