2025/05/30 by Runnan Lu, Yuxuan Zhang, Lu, Runnan +7 · 7 citations
Computer Science · Engineering · #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Motion and Animation #Interpolation (computer graphics) #Noisy text analytics #Rendering (computer graphics) #Text detection #Text recognition #Transformer #Video Analysis and Summarization #Visualization
paper · pdf · doi:10.48550/arxiv.2505.24417
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2025/05/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Generating accurate multilingual text with diffusion models has long been desired but remains challenging. Recent methods have made progress in rendering text in a single language, but rendering arbitrary languages is still an unexplored area. This paper introduces EasyText, a text rendering framework based on DiT (Diffusion Transformer), which connects denoising latents with multilingual character tokens encoded as character tokens. We propose character positioning encoding and position encoding interpolation techniques to achieve controllable and precise text rendering. Additionally, we construct a large-scale synthetic text image dataset with 1 million multilingual image-text annotations as well as a high-quality dataset of 20K annotated images, which are used for pretraining and fine-tuning respectively. Extensive experiments and evaluations demonstrate the effectiveness and advancement of our approach in multilingual text rendering, visual quality, and layout-aware text integration.