TextCtrl：基于扩散的先验引导控制场景文本编辑
TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control
AI总结：
提出基于扩散的场景文本编辑方法TextCtrl，通过风格-结构引导和字形自适应互自注意力机制提升风格一致性与渲染准确性，并构建首个真实世界图像对数据集ScenePair验证有效性。
摘要：
场景文本编辑（STE）以内容修改和风格保留为中心，尽管近期在文本到图像合成和文本驱动图像处理方面取得了显著进展，但仍然是一项具有挑战性的任务。基于GAN的STE方法通常遇到模型泛化的常见问题，而基于扩散的STE方法则面临不期望的风格偏差。为了解决这些问题，我们提出了TextCtrl，一种基于扩散的方法，通过先验引导控制来编辑文本。该方法包含两个关键组件：(i) 通过构建细粒度的文本风格解耦和鲁棒的文本字形结构表示，TextCtrl将风格-结构引导显式融入模型设计和网络训练中，显著提升了文本风格一致性和渲染准确性。(ii) 为了进一步利用风格先验，提出了字形自适应互自注意力机制，该机制解构源图像的隐式细粒度特征，以在推理期间增强风格一致性和视觉质量。此外，为填补真实世界STE评估基准的空白，我们创建了首个真实世界图像对数据集ScenePair，用于公平比较。实验表明，与先前方法相比，TextCtrl在风格保真度和文本准确性方面均表现出有效性。
英文摘要：
Centred on content modification and style preservation, Scene Text Editing (STE) remains a challenging task despite considerable progress in text-to-image synthesis and text-driven image manipulation recently. GAN-based STE methods generally encounter a common issue of model generalization, while Diffusion-based STE methods suffer from undesired style deviations. To address these problems, we propose TextCtrl, a diffusion-based method that edits text with prior guidance control. Our method consists of two key components: (i) By constructing fine-grained text style disentanglement and robust text glyph structure representation, TextCtrl explicitly incorporates Style-Structure guidance into model design and network training, significantly improving text style consistency and rendering accuracy. (ii) To further leverage the style prior, a Glyph-adaptive Mutual Self-attention mechanism is proposed which deconstructs the implicit fine-grained features of the source image to enhance style consistency and vision quality during inference. Furthermore, to fill the vacancy of the real-world STE evaluation benchmark, we create the first real-world image-pair dataset termed ScenePair for fair comparisons. Experiments demonstrate the effectiveness of TextCtrl compared with previous methods concerning both style fidelity and text accuracy.
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。
