Generative Phomosaic with Structure-Aligned and Personalized Diffusion

TL;DR

This paper introduces a novel generative approach to photomosaic creation using diffusion models conditioned on reference images, enhancing diversity and structural coherence beyond traditional methods.

Contribution

It presents the first generative photomosaic framework that synthesizes tiles with structure alignment and personalization, overcoming limitations of matching-based techniques.

Findings

Generative photomosaics achieve higher structural coherence.

The method allows for user-specific and stylistically consistent tiles.

It outperforms traditional matching-based photomosaic approaches.

Abstract

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.