EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Skeleton-Aware Deformable Alignment for Few-Shot Font Generation

Songshui Wu, Guangyong Zheng, Tao Jiang, Jinke Yang

Computers · 26.06.2026 · 15 (7) · 411

DOI: 10.3390/computers15070411 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computers, online erschienen am 26.06.2026. Verfasst von Songshui Wu und 3 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Open Fund of Hunan Provincial Key Laboratory of Intelligent Information Processing and Application for Hengyang Normal University, Horizontal Research Project of Hengyang Normal University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Few-shot font generation can be viewed as a challenging conditional image generation task, where the goal is to synthesize target glyphs from only a few reference samples while preserving structural fidelity and style consistency. This problem becomes particularly difficult for characters with complex spatial layouts and fine-grained stroke topology, where existing methods often struggle to simultaneously maintain structural integrity, local continuity, and stylistic coherence under sparse-reference conditions. To address this issue, we propose a skeleton-aware deformable alignment framework for few-shot font generation. Specifically, explicit skeleton priors are introduced into the diffusion-based generation process to provide structural supervision during denoising. In addition, a structure-constrained deformable content alignment module is designed to improve local feature correspondence while suppressing unreasonable geometric deformation. We further develop a multi-module content aggregation strategy to jointly model global layout patterns and local stroke details through complementary multi-level representations. Extensive experiments demonstrate that the proposed method consistently outperforms state-of-the-art approaches in both quantitative and qualitative evaluations. The results show that our method provides stronger structural preservation, better perceptual quality, and improved generalization in structurally complex glyph generation and cross-lingual style transfer.

Förderung

  • National Natural Science Foundation of China
  • Open Fund of Hunan Provincial Key Laboratory of Intelligent Information Processing and Application for Hengyang Normal University
  • Horizontal Research Project of Hengyang Normal University

Zitieren

APA

Wu, S., Zheng, G., Jiang, T., & Yang, J. (2026). Skeleton-Aware Deformable Alignment for Few-Shot Font Generation. Computers, 15(7), 411. https://doi.org/10.3390/computers15070411

Vancouver

Wu S, Zheng G, Jiang T, Yang J. Skeleton-Aware Deformable Alignment for Few-Shot Font Generation. Computers. 2026;15(7):411. doi:10.3390/computers15070411

BibTeX
@article{Wu2026,
  author = {Wu, Songshui and Zheng, Guangyong and Jiang, Tao and Yang, Jinke},
  title = {Skeleton-Aware Deformable Alignment for Few-Shot Font Generation},
  journal = {Computers},
  year = {2026},
  volume = {15},
  number = {7},
  pages = {411},
  doi = {10.3390/computers15070411}
}
Kostenlos starten →