Tiled Diffusion

Computer Vision & Graphics Lab, Reichman University
Interpolate start reference image.

Tiled Diffusion is a novel approach for generating seamlessly tileable images using diffusion models.

Abstract

Image tiling—the seamless connection of disparate images to create a coherent visual field—is crucial for applications such as texture creation, video game asset development, and digital art. Traditionally, tiles have been constructed manually, a method that poses significant limitations in scalability and flexibility. Recent research has attempted to automate this process using generative models. However, current approaches primarily focus on tiling textures and manipulating models for single-image generation, without inherently supporting the creation of multiple interconnected tiles across diverse domains. This paper presents Tiled Diffusion, a novel approach that extends the capabilities of diffusion models to accommodate the generation of cohesive tiling patterns across various domains of image synthesis that require tiling. Our method supports a wide range of tiling scenarios, from self-tiling to complex many-to-many connections, enabling seamless integration of multiple images. Tiled Diffusion automates the tiling process, eliminating the need for manual intervention and enhancing creative possibilities in various applications, such as seamlessly tiling of existing images, tiled texture creation, and 360° synthesis.

Method

Interpolate start reference image.

An example of a many-to-many tiling scenario demonstrating tiling / similarity constraint on the left side of the first image

Self-Tiling

The results are a single image tiled [1x3]

One-To-One Tiling

The results are two images tiled [1x4]

Many-To-Many Tiling

The results are two images tiled [1x4]

The results are three images tiled [3x3]

Tiled Texture Synthesis

Each of the results is a texture tiled [2x2] with itself

360° Synthesis

Left: Original image synthesised as a wrapped 360° view

Right: Horizontally translated version of it to demonstrate the wrapping

Seamlessly Tiling Existing Images

Left: Original image tiled [1x3]

Right: Transformed image tiled [1x3]

BibTeX

@misc{madar2024tileddiffusion,
      title={Tiled Diffusion},
      author={Or Madar and Ohad Fried},
      year={2024},
      eprint={2412.15185},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2412.15185},
}