Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods
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 ...
| Authors | Xingsong Ye, Yongkun Du, Jiaxin Zhang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 23 June 2026 |
| Last updated at source | 23 June 2026 |
Connected in the knowledge graph
- Yesianrohn/WATER-DataDataset · cited by
Models and datasets referencing this paper
- Yesianrohn/WATER-DataDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.