迈向免训练的场景文本编辑
Towards Training-free Scene Text Editing
把「流形引导 + 注意力增强」做成无需训练的即插即用模块，可直接迁移到任意扩散/流模型的图像局部编辑任务（如文字替换、风格保持修复），省去逐任务微调与配对数据。
原文依据 a training-free scene text editing framework that integrates the strengths of Attention Boost (AttnBoost) and Flow Manifold Steering (FMS)
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论场景文本编辑旨在修改自然图像中的文本内容，同时保持视觉真实感与语义一致性。现有方法通常需要任务特定的训练或配对数据，限制了其可扩展性与适应性。本文提出 TextFlow，一个免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，无需额外训练即可实现灵活、高保真的文本操控。具体而言，FMS 通过对字符与背景区域的视觉流进行建模来保持结构与风格一致性，而 AttnBoost 则通过基于注意力的引导增强文本内容的渲染。通过联合利用这两个互补模块，本方法以即插即用的方式，经由语义对齐与空间细化完成端到端的文本编辑。大量实验表明，本框架在视觉质量与文本准确度上达到与基于训练的方法相当或更优的水平，并在多样场景与语言上具有良好的泛化能力。本研究推动场景文本编辑朝向更高效、更可泛化、免训练的范式发展。
英文原文摘要 1219 字符
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.