EUVIMEDEUVIMED entdecken
Crossref

TripleFDS: Triple Feature Disentanglement and Synthesis for Scene Text Editing

Yuchen Bao, Yiting Wang, Wenjian Huang, Haowei Wang, Shen Chen, Taiping Yao, Shouhong Ding, Jianguo Zhang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (4) · 2417-2425

DOI: 10.1609/aaai.v40i4.37227 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yuchen Bao und 7 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Scene Text Editing (STE) aims to naturally modify text in images while preserving visual consistency, the decisive factors of which can be divided into three parts, i.e., text style, text content, and background. Previous methods have struggled with incomplete disentanglement of editable attributes, typically addressing only one aspect—such as editing text content—thus limiting controllability and visual consistency. To overcome these limitations, we propose TripleFDS, a novel framework for STE with disentangled modular attributes, and an accompanying dataset called SCB Synthesis. SCB Synthesis provides robust training data for triple feature disentanglement by utilizing the "SCB Group", a novel construct that combines three attributes per image to generate diverse, disentangled training groups. Leveraging this construct as a basic training unit, TripleFDS first disentangles triple features, ensuring semantic accuracy through inter-group contrastive regularization and preventing redundancy through intra-sample multi-feature orthogonality. In the synthesis phase, TripleFDS performs feature remapping to prevent "shortcut" phenomena during reconstruction and mitigate potential feature leakage. Trained on 125,000 SCB Groups, TripleFDS achieves state-of-the-art image fidelity (SSIM of 44.54) and text accuracy (ACC of 93.58%) on the mainstream STE benchmarks. Besides superior performance, the more flexible editing of TripleFDS supports new operations such as style replacement and background transfer.

Zitieren

APA

Bao, Y., Wang, Y., Huang, W., Wang, H., Chen, S., Yao, T., Ding, S., & Zhang, J. (2026). TripleFDS: Triple Feature Disentanglement and Synthesis for Scene Text Editing. Proceedings of the AAAI Conference on Artificial Intelligence, 40(4), 2417-2425. https://doi.org/10.1609/aaai.v40i4.37227

Vancouver

Bao Y, Wang Y, Huang W, Wang H, Chen S, Yao T, et al. TripleFDS: Triple Feature Disentanglement and Synthesis for Scene Text Editing. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(4):2417-2425. doi:10.1609/aaai.v40i4.37227

BibTeX
@article{Bao2026,
  author = {Bao, Yuchen and Wang, Yiting and Huang, Wenjian and Wang, Haowei and Chen, Shen and Yao, Taiping and Ding, Shouhong and Zhang, Jianguo},
  title = {TripleFDS: Triple Feature Disentanglement and Synthesis for Scene Text Editing},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {4},
  pages = {2417--2425},
  doi = {10.1609/aaai.v40i4.37227}
}
Kostenlos starten →