Content-aware Tile Generation using Exterior Boundary Inpainting

TL;DR

This paper introduces a flexible, diffusion model-based method for generating diverse, tileable image sets guided by exterior boundary conditions and text prompts, enabling high-quality tiling without retraining.

Contribution

It proposes a novel boundary-guided inpainting approach using pretrained diffusion models for content-aware tile generation, including a new Dual Wang tiling scheme for improved diversity.

Findings

Effective generation of tileable images from text prompts

Enhanced texture continuity with Dual Wang tiling

No retraining needed for different tiling schemes

Abstract

We present a novel and flexible learning-based method for generating tileable image sets. Our method goes beyond simple self-tiling, supporting sets of mutually tileable images that exhibit a high degree of diversity. To promote diversity we decouple structure from content by foregoing explicit copying of patches from an exemplar image. Instead we leverage the prior knowledge of natural images and textures embedded in large-scale pretrained diffusion models to guide tile generation constrained by exterior boundary conditions and a text prompt to specify the content. By carefully designing and selecting the exterior boundary conditions, we can reformulate the tile generation process as an inpainting problem, allowing us to directly employ existing diffusion-based inpainting models without the need to retrain a model on a custom training set. We demonstrate the flexibility and efficacy of our content-aware tile generation method on different tiling schemes, such as Wang tiles, from only a text prompt. Furthermore, we introduce a novel Dual Wang tiling scheme that provides greater texture continuity and diversity than existing Wang tile variants.