arXiv 2603.245712026-03-25cs.CV

无训练场景文本编辑

Towards Training-Free Scene Text Editing

School of Cyber Science and Engineering（网络安全科学与工程学院）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；State Key Laboratory of Cyberspace Security Defense（网络空间安全防御国家重点实验室）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院）

Yubo Li, Xugong Qin, Peng Zhang, Hailun Lin, Gangyan Zeng, Kexin Zhang

备注：: Accepted by CVPR 2026

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出TextFlow框架，通过结合Attention Boost和Flow Manifold Steering方法，实现无需额外训练的高保真文本编辑，实验表明其在视觉质量和文本准确性上优于传统方法。

摘要：

场景文本编辑旨在在自然图像中修改文本内容，同时保持视觉真实性和语义一致性。现有方法通常需要任务特定训练或配对数据，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，整合了Attention Boost（AttnBoost）和Flow Manifold Steering（FMS）的优势，以实现灵活、高保真的文本操作。具体而言，FMS通过建模字符和背景区域的视觉流来保持结构和风格一致性，而AttnBoost通过基于注意力的指导增强文本内容的渲染。通过联合利用这些互补模块，我们的方法通过语义对齐和空间细化，以即插即用的方式实现端到端的文本编辑。大量实验表明，我们的框架在视觉质量和文本准确性上与传统方法相当或更优，能够良好泛化到多样化的场景和语言中。本研究推动了场景文本编辑向更高效、通用和无训练的方向发展。代码可在https://github.com/lyb18758/TextFlow获取。

英文摘要：

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

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。