推进基于WordArt的场景文本识别研究：数据集与方法
Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods
摘要
WordArt（艺术性文本）具有高度可定制的字体、纹理和布局特性，因此与普通的场景文本识别任务相比，基于WordArt的场景文本识别任务要更加困难。现有的场景文本识别数据集和方法通常基于规则化的场景文本和固定模板输入，难以适用于WordArt场景。因此，我们试图从数据和模型两个层面来改进这一任务。在数据方面，我们构建了一个包含200万条样本的合成数据集WATER-S，其规模比现有的艺术性文本数据大了数百倍。WATER-S由两个互补的子集组成：一个通过升级后的渲染流程SynthWordArt生成，能够产生高度准确且可控制的合成WordArt数据；另一个则通过结合Qwen3-VL用于提示词生成以及Z-Image用于图像合成来生成，从而增加了真实且多样化的数据量。在模型方面，我们提出了WATERec模型。该模型采用支持任意形状输入的视觉编码器以及自回归解码器，能够处理复杂的布局情况，从而解决了固定模板下的场景文本识别的瓶颈问题。实验表明，这种架构优于现有的场景文本识别方法，在不规则文本如WordArt上取得了最先进的性能。结合从现有真实场景文本数据中精心整理出的WATER-R，加上新的合成数据和模型设计，我们的模型在WordArt-Bench测试集上的准确率达到了90.40%，远远超过了通用视觉语言模型和OCR专用视觉语言模型。代码和数据可在https://github.com/YesianRohn/WATER获取。
English 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.