SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Maps

TL;DR

SeamlessGAN is a novel self-supervised method that generates high-quality, tileable multi-layered texture maps from a single example by leveraging a latent space tiling approach and discriminator-based artifact detection.

Contribution

It introduces a unified approach for simultaneous texture synthesis and tileability, working with multi-layered textures and improving quality over previous methods.

Findings

Outperforms previous texture synthesis methods quantitatively and qualitatively.

Successfully generates tileable textures with multiple maps like albedo and normals.

Works effectively across various texture types.

Abstract

We present SeamlessGAN, a method capable of automatically generating tileable texture maps from a single input exemplar. In contrast to most existing methods, focused solely on solving the synthesis problem, our work tackles both problems, synthesis and tileability, simultaneously. Our key idea is to realize that tiling a latent space within a generative network trained using adversarial expansion techniques produces outputs with continuity at the seam intersection that can be then be turned into tileable images by cropping the central area. Since not every value of the latent space is valid to produce high-quality outputs, we leverage the discriminator as a perceptual error metric capable of identifying artifact-free textures during a sampling process. Further, in contrast to previous work on deep texture synthesis, our model is designed and optimized to work with multi-layered texture representations, enabling textures composed of multiple maps such as albedo, normals, etc. We extensively test our design choices for the network architecture, loss function and sampling parameters. We show qualitatively and quantitatively that our approach outperforms previous methods and works for textures of different types.