无需训练即可高保真编辑自然图像中的文字内容。
Towards Training-Free Scene Text Editing
- 融合注意力增强与流形引导，实现无训练文本编辑。
- 在多种场景和语言上保持文字准确性和视觉真实感。
- 插件式设计，适合快速部署到现有图像编辑系统。
场景文本编辑旨在修改自然图像中的文字内容，同时保持视觉真实性和语义一致性。现有方法通常需要特定任务的训练或成对数据，限制了其可扩展性和适应性。本文提出 TextFlow，一种无需训练的场景文本编辑框架，融合注意力增强（AttnBoost）与流形引导（FMS）的优势，实现灵活、高保真的文本操作而无需额外训练。具体而言，FMS通过建模字符与背景区域的视觉流，保持结构与风格一致性；AttnBoost则通过基于注意力的引导提升文本渲染效果。通过联合利用这两个互补模块，该方法通过语义对齐与空间精修实现端到端文本编辑，具备即插即用特性。大量实验表明，该框架在视觉质量与文本准确性上达到甚至超越训练型方法，且在多样场景与语言下具有良好泛化能力。本研究推动了场景文本编辑向更高效、通用和免训练的方向发展。代码已开源：https://github.com/lyb18758/TextFlow。
原文摘要 · Abstract (English)
Scene text editing seeks to modify textual content in natural images while maintaining visual realism and semantic consistency. Existing methods often require task-specific training or paired data, limiting their scalability and adaptability. In this paper, we propose TextFlow, a training-free scene text editing framework that integrates the strengths of Attention Boost (AttnBoost) and Flow Manifold Steering (FMS) to enable flexible, high-fidelity text manipulation without additional training. Specifically, FMS preserves the structural and style consistency by modeling the visual flow of characters and background regions, while AttnBoost enhances the rendering of textual content through attention-based guidance. By jointly leveraging these complementary modules, our approach performs end-to-end text editing through semantic alignment and spatial refinement in a plug-and-play manner. Extensive experiments demonstrate that our framework achieves visual quality and text accuracy comparable to or superior to those of training-based counterparts, generalizing well across diverse scenes and languages. This study advances scene text editing toward a more efficient, generalizable, and training-free paradigm. Code is available at https://github.com/lyb18758/TextFlow
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。