FASTER: A Font-Agnostic Scene Text Editing and Rendering Framework
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916467777208320 |
|---|---|
| author | Das, Alloy Biswas, Sanket Roy, Prasun Ghosh, Subhankar Pal, Umapada Blumenstein, Michael Lladós, Josep Bhattacharya, Saumik |
| author_facet | Das, Alloy Biswas, Sanket Roy, Prasun Ghosh, Subhankar Pal, Umapada Blumenstein, Michael Lladós, Josep Bhattacharya, Saumik |
| contents | Scene Text Editing (STE) is a challenging research problem, that primarily aims towards modifying existing texts in an image while preserving the background and the font style of the original text. Despite its utility in numerous real-world applications, existing style-transfer-based approaches have shown sub-par editing performance due to (1) complex image backgrounds, (2) diverse font attributes, and (3) varying word lengths within the text. To address such limitations, in this paper, we propose a novel font-agnostic scene text editing and rendering framework, named FASTER, for simultaneously generating text in arbitrary styles and locations while preserving a natural and realistic appearance and structure. A combined fusion of target mask generation and style transfer units, with a cascaded self-attention mechanism has been proposed to focus on multi-level text region edits to handle varying word lengths. Extensive evaluation on a real-world database with further subjective human evaluation study indicates the superiority of FASTER in both scene text editing and rendering tasks, in terms of model performance and efficiency. Our code will be released upon acceptance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_02905 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | FASTER: A Font-Agnostic Scene Text Editing and Rendering Framework Das, Alloy Biswas, Sanket Roy, Prasun Ghosh, Subhankar Pal, Umapada Blumenstein, Michael Lladós, Josep Bhattacharya, Saumik Computer Vision and Pattern Recognition Multimedia Scene Text Editing (STE) is a challenging research problem, that primarily aims towards modifying existing texts in an image while preserving the background and the font style of the original text. Despite its utility in numerous real-world applications, existing style-transfer-based approaches have shown sub-par editing performance due to (1) complex image backgrounds, (2) diverse font attributes, and (3) varying word lengths within the text. To address such limitations, in this paper, we propose a novel font-agnostic scene text editing and rendering framework, named FASTER, for simultaneously generating text in arbitrary styles and locations while preserving a natural and realistic appearance and structure. A combined fusion of target mask generation and style transfer units, with a cascaded self-attention mechanism has been proposed to focus on multi-level text region edits to handle varying word lengths. Extensive evaluation on a real-world database with further subjective human evaluation study indicates the superiority of FASTER in both scene text editing and rendering tasks, in terms of model performance and efficiency. Our code will be released upon acceptance. |
| title | FASTER: A Font-Agnostic Scene Text Editing and Rendering Framework |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2308.02905 |