FASTER: A Font-Agnostic Scene Text Editing and Rendering Framework
This addresses the challenge of editing text in complex scene images for applications like image manipulation, though it appears incremental as it builds on style-transfer approaches.
The paper tackles the problem of scene text editing by modifying text in images while preserving background and font style, proposing FASTER to generate text in arbitrary styles and locations with realistic appearance, achieving superior performance and efficiency in evaluations.
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.