TextMastero: Mastering High-Quality Scene Text Editing in Diverse Languages and Styles
This work solves the problem of accurate and style-consistent text editing in images for applications involving multilingual content, though it is incremental as it builds on diffusion models.
The paper tackles the problem of scene text editing, which modifies text on images while preserving style, by addressing challenges with complex backgrounds and non-Latin languages like CJK characters, resulting in a method that surpasses existing works in text fidelity and style similarity.
Scene text editing aims to modify texts on images while maintaining the style of newly generated text similar to the original. Given an image, a target area, and target text, the task produces an output image with the target text in the selected area, replacing the original. This task has been studied extensively, with initial success using Generative Adversarial Networks (GANs) to balance text fidelity and style similarity. However, GAN-based methods struggled with complex backgrounds or text styles. Recent works leverage diffusion models, showing improved results, yet still face challenges, especially with non-Latin languages like CJK characters (Chinese, Japanese, Korean) that have complex glyphs, often producing inaccurate or unrecognizable characters. To address these issues, we present \emph{TextMastero} - a carefully designed multilingual scene text editing architecture based on latent diffusion models (LDMs). TextMastero introduces two key modules: a glyph conditioning module for fine-grained content control in generating accurate texts, and a latent guidance module for providing comprehensive style information to ensure similarity before and after editing. Both qualitative and quantitative experiments demonstrate that our method surpasses all known existing works in text fidelity and style similarity.