| title | Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods |
|---|---|
| authors | Xingsong Ye, Yongkun Du, Jiaxin Zhang, Haojie Zhang, Chong Sun, Chen Li, Jing Lyu, Zhineng Chen |
| date | 2026-06-23 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.24484 |
| affiliation | Fudan University |
| upvotes | 6 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | WordArt (artistic text) features highly customized fonts, textures, and layouts, making WordArt-oriented scene TExt Recognition (WATER) substantially more challenging than general Scene Text Recognition (STR). Existing STR datasets and methods, typically built around regular scene text and fixed-template inputs, struggle to scale to WATER. Thus, we aim to advance this task from both data and model perspectives. On the data side, we construct a 2M synthetic dataset, WATER-S, with the scale improved by hundreds of times compared to existing artistic text data. WATER-S consists of two complementary subsets. One rendered by an upgraded rendering pipeline (SynthWordArt), which provides highly accurate and controllable synthetic WordArt data. The other is generated by combining Qwen3-VL for prompt mining and Z-Image for image synthesis, which improves the coverage of realistic and diverse data. On the model side, we propose WATERec. It adopts an visual encoder supporting arbitrary-shaped inputs and an autoregressive decoder to model complex layouts, structurally breaking the bottleneck of fixed-template STR on WordArt. Experiments show that this architecture outperforms prior STR methods, achieving state-of-the-art performance on irregular texts such as WordArt. Together with WATER-R, carefully reorganized from existing real STR data, our strong baseline with the new synthetic data and model design reaches 90.40% accuracy on WordArt-Bench, surpassing both general-purpose and OCR-specialized vision-language models by a large margin. Code and data are available at https://github.com/YesianRohn/WATER. |
cite
@misc{ye2026advancing,
title={Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods},
author={Xingsong Ye and Yongkun Du and Jiaxin Zhang and Haojie Zhang and Chong Sun and Chen Li and Jing Lyu and Zhineng Chen},
year={2026},
eprint={2606.24484},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.24484}
}