StyleTextGen: Style-Conditioned Multilingual Scene Text Generation

2026-05-14

AI Summary

This work addresses the challenges of style extraction and character-level style consistency in multilingual scene text under complex backgrounds. To this end, we propose StyleTextGen, a novel framework featuring a dual-branch style encoder to model cross-lingual text styles, a style consistency loss to enforce uniformity at the character level, and a mask-guided inference strategy to enhance generation quality. We further introduce StyleText-CE, the first bilingual scene text style benchmark, and demonstrate that our method achieves state-of-the-art performance in style-faithful and cross-lingually generalizable text generation, significantly outperforming existing approaches in both style preservation and multilingual adaptability.

Abstract

Style-conditioned scene text generation faces unique challenges in extracting precise text styles from complex backgrounds and maintaining fine-grained style consistency across characters, especially for multilingual scripts. We propose StyleTextGen, a novel framework that learns to perceive and replicate visual text styles across different languages and writing systems. Our approach features three key contributions: First, we introduce a dual-branch style encoder dedicated to style modeling, yielding robust multilingual text style representations in complex real-world scenes. Second, we design a text style consistency loss that enhances style coherence and improves overall visual quality. Third, we develop a mask-guided inference strategy that ensures precise style alignment between generated and reference text. To facilitate systematic evaluation, we construct StyleText-CE, a bilingual scene text style benchmark covering both monolingual and cross-lingual settings. Extensive experiments demonstrate that StyleTextGen significantly outperforms existing methods in style consistency and cross-lingual generalization, establishing new state-of-the-art performance in multilingual style-conditioned text generation.

Problem

• style-conditioned
• multilingual
• scene text generation
• style consistency
• cross-lingual

Innovation

• style-conditioned generation
• multilingual scene text
• dual-branch style encoder
• style consistency loss
• mask-guided inference