Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.14708 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911685645697024 |
|---|---|
| author | Chen, Zeyu Zhao, Fangmin Shu, Yan Liu, Yichao Yu, Liu Zhou, Yu |
| author_facet | Chen, Zeyu Zhao, Fangmin Shu, Yan Liu, Yichao Yu, Liu Zhou, Yu |
| contents | Style-conditioned scene text generation faces unique challenges in extracting precise text styles from complex backgrounds and maintaining fine-grained style consistency across characters, especially for multilingual scripts. We propose StyleTextGen, a novel framework that learns to perceive and replicate visual text styles across different languages and writing systems. Our approach features three key contributions: First, we introduce a dual-branch style encoder dedicated to style modeling, yielding robust multilingual text style representations in complex real-world scenes. Second, we design a text style consistency loss that enhances style coherence and improves overall visual quality. Third, we develop a mask-guided inference strategy that ensures precise style alignment between generated and reference text. To facilitate systematic evaluation, we construct StyleText-CE, a bilingual scene text style benchmark covering both monolingual and cross-lingual settings. Extensive experiments demonstrate that StyleTextGen significantly outperforms existing methods in style consistency and cross-lingual generalization, establishing new state-of-the-art performance in multilingual style-conditioned text generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_14708 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | StyleTextGen: Style-Conditioned Multilingual Scene Text Generation Chen, Zeyu Zhao, Fangmin Shu, Yan Liu, Yichao Yu, Liu Zhou, Yu Computer Vision and Pattern Recognition Style-conditioned scene text generation faces unique challenges in extracting precise text styles from complex backgrounds and maintaining fine-grained style consistency across characters, especially for multilingual scripts. We propose StyleTextGen, a novel framework that learns to perceive and replicate visual text styles across different languages and writing systems. Our approach features three key contributions: First, we introduce a dual-branch style encoder dedicated to style modeling, yielding robust multilingual text style representations in complex real-world scenes. Second, we design a text style consistency loss that enhances style coherence and improves overall visual quality. Third, we develop a mask-guided inference strategy that ensures precise style alignment between generated and reference text. To facilitate systematic evaluation, we construct StyleText-CE, a bilingual scene text style benchmark covering both monolingual and cross-lingual settings. Extensive experiments demonstrate that StyleTextGen significantly outperforms existing methods in style consistency and cross-lingual generalization, establishing new state-of-the-art performance in multilingual style-conditioned text generation. |
| title | StyleTextGen: Style-Conditioned Multilingual Scene Text Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.14708 |