Global Prompt: "A cat with flower background"
Local Prompt: "A Cat"
TL;DR. A generative photomosaic framework that synthesizes structure-aligned mosaics and supports few-shot personalization.
Global Prompt: "A cat with flower background"
Local Prompt: "A Cat"
TL;DR. A generative photomosaic framework that synthesizes structure-aligned mosaics and supports few-shot personalization.
We present the first generative approach to photomosaic creation. Traditional photomosaic methods rely on a large number of tile images and color-based matching, which limits both diversity and structural consistency. Our generative photomosaic framework synthesizes tile images using diffusion-based generation conditioned on reference images. A low-frequency–conditioned diffusion mechanism aligns global structure while preserving prompt-driven details. This generative formulation enables photomosaic composition that is both semantically expressive and structurally coherent, effectively overcoming the fundamental limitations of matching-based approaches. By leveraging few-shot personalized diffusion, our model is able to produce user-specific or stylistically consistent tiles without requiring an extensive collection of images.
@article{chung2025from,
title={From Matching to Generation: Generative Photomosaics with Structure-Aligned and Personalized Diffusion},
author={Jaeyoung Chung, Hyunjin Son, Kyoung Mu Lee},
journal={arXiv preprint arXiv:},
year={2025}
}