Metraipolis › archive › dc_e65cdd48852f

CoDeFont: One-Shot Font Generation via Multi-Scale Factor-Specific Representation Learning — arXiv:2610.21364

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21364
License (as archived)
CC0-1.0
Archived
2026-10-16T10:35:17.253Z
SHA-256 of the archived text
ca6bdaf62773b42efdc86f9886bb6c27b1b99298a9e8a91a8efbe5c610ff725a
Stable URL of this page
https://metraipolis.com/documento/dc_e65cdd48852f

How to cite

CoDeFont: One-Shot Font Generation via Multi-Scale Factor-Specific Representation Learning — arXiv:2610.21364 — arXiv (en), https://arxiv.org/abs/2610.21364 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e65cdd48852f (Metraipolis archive dc_e65cdd48852f, sha256 ca6bdaf62773b42efdc86f9886bb6c27b1b99298a9e8a91a8efbe5c610ff725a)
BibTeX
@misc{dce65cdd48852f,
  title = {CoDeFont: One-Shot Font Generation via Multi-Scale Factor-Specific Representation Learning — arXiv:2610.21364},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21364},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e65cdd48852f; sha256 ca6bdaf62773b42efdc86f9886bb6c27b1b99298a9e8a91a8efbe5c610ff725a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21364. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

One-shot Font Generation (OFG) aims to synthesize a target glyph by transferring the stylistic characteristics of a single reference glyph while preserving the structure of the target character. However, accurately capturing font style from a single reference image remains challenging due to the limited stylistic information available in a single glyph, and this challenge is further amplified for complex scripts. We propose CoDeFont, a script-agnostic OFG framework that addresses this challenge through multi-level style-content factorization and progressive style-content reconciliation. CoDeFont independently aggregates complementary style and structural information across multiple spatial levels to obtain factor-specific representations, while a contrastive objective explicitly encourages separation between style and content embeddings. During reconstruction, the disentangled representations are progressively injected through multi-level style conditioning, enabling stylistic information to be incorporated at different decoding resolutions while preserving the underlying glyph structure. We evaluate CoDeFont on structurally distinct Bengali and Latin scripts across seen and unseen font styles. Extensive quantitative and qualitative analyses demonstrate consistent improvements over existing state-of-the-art methods, highlighting the effectiveness of the proposed framework for OFG across diverse writing systems.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.21364 — 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 2026-10-16T08:52:02.655Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).