推進面向藝術字的場景文字識別：數據集與方法

摘要

WordArt（藝術字）具備高度自訂的字型、紋理與排版特性，使得以藝術字為導向的場景文字辨識（WATER）任務遠比一般場景文字辨識（STR）更具挑戰性。現有的STR資料集與方法通常基於常規場景文字與固定模板輸入設計，難以有效擴展至WATER任務。為此，我們旨在從資料與模型雙層面推動此任務的進展。在資料層面，我們構建了名為WATER-S的200萬筆合成資料集，其規模較現有藝術字資料提升數百倍。WATER-S包含兩個互補子集：其一由升級後的渲染管線（SynthWordArt）生成，提供高度精確且可控的合成藝術字資料；其二則結合Qwen3-VL進行提示挖掘與Z-Image進行影像合成，提升真實多樣資料的覆蓋率。在模型層面，我們提出WATERec架構，採用支援任意形狀輸入的視覺編碼器與自迴歸解碼器來建模複雜排版，從結構上突破固定模板STR在藝術字上的瓶頸。實驗顯示此架構優於既有STR方法，在藝術字等不規則文字上達到最先進水準。結合從現有真實STR資料精心重整的WATER-R，我們以新合成資料與模型設計建立的強基線，在WordArt-Bench上達到90.40%準確率，大幅超越通用型與OCR專用視覺語言模型。程式碼與資料已公開於 https://github.com/YesianRohn/WATER。

English

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.