Generative Phomosaic with Structure-Aligned and Personalized Diffusion
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910112743948288 |
|---|---|
| author | Chung, Jaeyoung Son, Hyunjin Lee, Kyoung Mu |
| author_facet | Chung, Jaeyoung Son, Hyunjin Lee, Kyoung Mu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_06989 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Generative Phomosaic with Structure-Aligned and Personalized Diffusion Chung, Jaeyoung Son, Hyunjin Lee, Kyoung Mu Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | Generative Phomosaic with Structure-Aligned and Personalized Diffusion |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2604.06989 |