Beyond Flat Text: Dual Self-inherited Guidance for Visual Text Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917966030831616 |
|---|---|
| author | Luo, Minxing Xia, Zixun Chen, Liaojun Li, Zhenhang Zeng, Weichao Wang, Jianye Cheng, Wentao Wang, Yaxing Zhou, Yu Yang, Jian |
| author_facet | Luo, Minxing Xia, Zixun Chen, Liaojun Li, Zhenhang Zeng, Weichao Wang, Jianye Cheng, Wentao Wang, Yaxing Zhou, Yu Yang, Jian |
| contents | In real-world images, slanted or curved texts, especially those on cans, banners, or badges, appear as frequently, if not more so, than flat texts due to artistic design or layout constraints. While high-quality visual text generation has become available with the advanced generative capabilities of diffusion models, these models often produce distorted text and inharmonious text background when given slanted or curved text layouts due to training data limitation. In this paper, we introduce a new training-free framework, STGen, which accurately generates visual texts in challenging scenarios (\eg, slanted or curved text layouts) while harmonizing them with the text background. Our framework decomposes the visual text generation process into two branches: (i) \textbf{Semantic Rectification Branch}, which leverages the ability in generating flat but accurate visual texts of the model to guide the generation of challenging scenarios. The generated latent of flat text is abundant in accurate semantic information related both to the text itself and its background. By incorporating this, we rectify the semantic information of the texts and harmonize the integration of the text with its background in complex layouts. (ii) \textbf{Structure Injection Branch}, which reinforces the visual text structure during inference. We incorporate the latent information of the glyph image, rich in glyph structure, as a new condition to further strengthen the text structure. To enhance image harmony, we also apply an effective combination method to merge the priors, providing a solid foundation for generation. Extensive experiments across a variety of visual text layouts demonstrate that our framework achieves superior accuracy and outstanding quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_05892 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Flat Text: Dual Self-inherited Guidance for Visual Text Generation Luo, Minxing Xia, Zixun Chen, Liaojun Li, Zhenhang Zeng, Weichao Wang, Jianye Cheng, Wentao Wang, Yaxing Zhou, Yu Yang, Jian Computer Vision and Pattern Recognition In real-world images, slanted or curved texts, especially those on cans, banners, or badges, appear as frequently, if not more so, than flat texts due to artistic design or layout constraints. While high-quality visual text generation has become available with the advanced generative capabilities of diffusion models, these models often produce distorted text and inharmonious text background when given slanted or curved text layouts due to training data limitation. In this paper, we introduce a new training-free framework, STGen, which accurately generates visual texts in challenging scenarios (\eg, slanted or curved text layouts) while harmonizing them with the text background. Our framework decomposes the visual text generation process into two branches: (i) \textbf{Semantic Rectification Branch}, which leverages the ability in generating flat but accurate visual texts of the model to guide the generation of challenging scenarios. The generated latent of flat text is abundant in accurate semantic information related both to the text itself and its background. By incorporating this, we rectify the semantic information of the texts and harmonize the integration of the text with its background in complex layouts. (ii) \textbf{Structure Injection Branch}, which reinforces the visual text structure during inference. We incorporate the latent information of the glyph image, rich in glyph structure, as a new condition to further strengthen the text structure. To enhance image harmony, we also apply an effective combination method to merge the priors, providing a solid foundation for generation. Extensive experiments across a variety of visual text layouts demonstrate that our framework achieves superior accuracy and outstanding quality. |
| title | Beyond Flat Text: Dual Self-inherited Guidance for Visual Text Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.05892 |