FASTER:一种与字体无关的场景文本编辑与渲染框架
FASTER: A Font-Agnostic Scene Text Editing and Rendering Framework
AI总结:
针对现有场景文本编辑方法在复杂背景、多样字体和变长文本下性能不佳的问题,提出一种与字体无关的编辑渲染框架FASTER,融合掩码生成、风格迁移与级联自注意力机制,在真实数据上验证了其优越性。
摘要:
场景文本编辑(STE)是一个具有挑战性的研究问题,其主要目标是在保留图像背景和原始文本字体风格的同时,修改图像中的现有文本。尽管该技术在众多实际应用中具有实用性,但现有的基于风格迁移的方法由于(1)复杂的图像背景、(2)多样的字体属性以及(3)文本中变化的单词长度,其编辑性能表现欠佳。为了解决这些局限性,本文提出了一种新颖的与字体无关的场景文本编辑与渲染框架,命名为FASTER,用于在保持自然逼真的外观和结构的同时,以任意风格和位置生成文本。我们提出了一种目标掩码生成与风格迁移单元的融合机制,并结合级联自注意力机制,以专注于多级文本区域编辑,从而处理不同的单词长度。在真实世界数据库上的广泛评估以及进一步的主观人工评估研究表明,FASTER在场景文本编辑和渲染任务中,在模型性能和效率方面均具有优越性。我们的代码将在论文被接收后发布。
英文摘要:
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.
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。