TextCrafter: Accurately Rendering Multiple Texts in Complex Visual Scenes
This addresses the challenge of accurately rendering multiple texts in visual scenes for applications in image generation, though it appears incremental as it builds on existing CVTG tasks.
The paper tackles the problem of generating complex visual text in images, where existing models often produce distorted or missing text, by proposing TextCrafter, a method that improves text rendering accuracy and outperforms state-of-the-art approaches in experiments.
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.