Metraipolis › archive › dc_294f2f4ec784
MegaStyle++: Scaling Image Style Space through Hierarchical Style Definition — arXiv:2609.01423
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01423
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:13:56.658Z
- SHA-256 of the archived text
918a9973063228d1ffcee4e0c0eddd55291e2616491dd7313b5693c931f48eb2- Stable URL of this page
https://metraipolis.com/documento/dc_294f2f4ec784
How to cite
MegaStyle++: Scaling Image Style Space through Hierarchical Style Definition — arXiv:2609.01423 — arXiv (en), https://arxiv.org/abs/2609.01423 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_294f2f4ec784 (Metraipolis archive dc_294f2f4ec784, sha256 918a9973063228d1ffcee4e0c0eddd55291e2616491dd7313b5693c931f48eb2)
BibTeX
@misc{dc294f2f4ec784,
title = {MegaStyle++: Scaling Image Style Space through Hierarchical Style Definition — arXiv:2609.01423},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01423},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_294f2f4ec784; sha256 918a9973063228d1ffcee4e0c0eddd55291e2616491dd7313b5693c931f48eb2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01423. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Image style is a highly abstract, human-constructed concept shaped by a range of visual factors and intrinsically entangled with content, yet a unified and explicit definition of image style remains lacking. In this work, we first discuss the fundamental question of what is style and then propose a hierarchical style definition that describes image style from an overall style identity to fine-grained visual attributes, providing a more structured, transferable, and interpretable style representation. Based on this definition, we refine the style annotation pipeline of MegaStyle and construct MegaStyle++-8M, a large-scale style dataset containing 150K overall style identities, 1M fine-grained style prompts, and 8M stylized images. Extensive analyses demonstrate that our hierarchical definition substantially expands the style space in both diversity and semantic breadth, while precisely capturing intrinsic visual style of reference images. The dataset and code will be updated at this https URL , we hope MegaStyle++ provides a scalable foundation for studying and modeling diverse image styles. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.01423 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T07:00:58.987Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).