TextCrafter：在复杂视觉场景中精准呈现多重文本

TextCrafter: Accurately Rendering Multiple Texts in Complex Visual Scenes

March 30, 2025

作者: Nikai Du, Zhennan Chen, Zhizhou Chen, Shan Gao, Xi Chen, Zhengkai Jiang, Jian Yang, Ying Tai

cs.AI

摘要

本文深入探讨了复杂视觉文本生成（CVTG）任务，该任务专注于在视觉图像的不同区域内生成分布式的精细文本内容。在CVTG中，图像生成模型常出现视觉文本扭曲、模糊或缺失的问题。为应对这些挑战，我们提出了TextCrafter，一种创新的多视觉文本渲染方法。TextCrafter采用渐进策略，将复杂视觉文本分解为独立组件，同时确保文本内容与其视觉载体之间的精准对齐。此外，该方法引入了令牌聚焦增强机制，以在生成过程中提升视觉文本的显著性。TextCrafter有效解决了CVTG任务中的关键难题，如文本混淆、遗漏和模糊。我们还推出了一个全新的基准数据集CVTG-2K，专门用于严格评估生成模型在CVTG任务上的表现。大量实验证明，我们的方法超越了当前最先进的技术。

English

This paper explores the task of Complex Visual Text Generation (CVTG), which centers on generating intricate textual content distributed across diverse regions within visual images. In CVTG, image generation models often rendering distorted and blurred visual text or missing some visual text. To tackle these challenges, we propose TextCrafter, a novel multi-visual text rendering method. TextCrafter employs a progressive strategy to decompose complex visual text into distinct components while ensuring robust alignment between textual content and its visual carrier. Additionally, it incorporates a token focus enhancement mechanism to amplify the prominence of visual text during the generation process. TextCrafter effectively addresses key challenges in CVTG tasks, such as text confusion, omissions, and blurriness. Moreover, we present a new benchmark dataset, CVTG-2K, tailored to rigorously evaluate the performance of generative models on CVTG tasks. Extensive experiments demonstrate that our method surpasses state-of-the-art approaches.