EUVIMEDEUVIMED entdecken
Crossref

Enhanced Generative Structure Prior for Chinese Text Image Super-Resolution

Xiaoming Li, Wangmeng Zuo, Chen Change Loy

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-12 · 47 (12) · 11366-11381

DOI: 10.1109/tpami.2025.3596329 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-12. Verfasst von Xiaoming Li und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 98 Literaturangaben. Gefördert von: RIE2020 Industry Alignment Fund Industry Collaboration Projects, Funding Initiative, kind contribution from the industry partner.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Faithful text image super-resolution (SR) is challenging because each character has a unique structure and usually exhibits diverse font styles and layouts. While existing methods primarily focus on English text, less attention has been paid to more complex scripts like Chinese. In this paper, we introduce a high-quality text image SR framework designed to restore the precise strokes of low-resolution (LR) Chinese characters. Unlike methods that rely on character recognition priors to regularize the SR task, we propose a novel structure prior that offers structure-level guidance to enhance visual quality. Our framework incorporates this structure prior within a StyleGAN model, leveraging its generative capabilities for restoration. To maintain the integrity of character structures while accommodating various font styles and layouts, we implement a codebook-based mechanism that restricts the generative space of StyleGAN. Each code in the codebook represents the structure of a specific character, while the vector $w$w in StyleGAN controls the character's style, including typeface, orientation, and location. Through the collaborative interaction between the codebook and style, we generate a high-resolution structure prior that aligns with LR characters both spatially and structurally. Experiments demonstrate that this structure prior provides robust, character-specific guidance, enabling the accurate restoration of clear strokes in degraded characters, even for real-world LR Chinese text with irregular layouts.

Förderung

  • RIE2020 Industry Alignment Fund Industry Collaboration Projects
  • Funding Initiative
  • kind contribution from the industry partner

Zitieren

APA

Li, X., Zuo, W., & Loy, C. C. (2025). Enhanced Generative Structure Prior for Chinese Text Image Super-Resolution. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(12), 11366-11381. https://doi.org/10.1109/tpami.2025.3596329

Vancouver

Li X, Zuo W, Loy CC. Enhanced Generative Structure Prior for Chinese Text Image Super-Resolution. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(12):11366-11381. doi:10.1109/tpami.2025.3596329

BibTeX
@article{Li2025,
  author = {Li, Xiaoming and Zuo, Wangmeng and Loy, Chen Change},
  title = {Enhanced Generative Structure Prior for Chinese Text Image Super-Resolution},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {12},
  pages = {11366--11381},
  doi = {10.1109/tpami.2025.3596329}
}
Kostenlos starten →