Research
Generative Phomosaic with Structure-Aligned and Personalized Diffusion
arXiv:2604.06989v1 Announce Type: cross Abstract: We present the first generative approach to photomosaic creation. Traditional photomosaic methods rely on a large number of tile images and color-base
arXiv:2604.06989v1 Announce Type: cross 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.
Related
- DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation
- Less is More: Data-Efficient Adaptation for Controllable Text-to-Video Generation
- On the Robustness of Diffusion-Based Image Compression to Bit-Flip Errors
- Physics-Informed Spectral Modeling for Hyperspectral Imaging
Source: arXiv cs.AI | 2026-04-10