一个模型认229种文字，比专用模型还准
现在手机拍路牌、菜单，识别多国文字要么每种语言装一个识别器(又贵又容易出错)，要么用超大视觉模型(慢且不准)。这篇论文做了一个折中：一个模型、一个视觉编码器，内部用「专家路由」把不同文字分给不同专家处理，同时共享一个专家吸收跨语言的共性。他们造了覆盖10种文字系统、229种语言的合成数据集来补真实数据的稀缺，最终在10种文字的基准上准确率82.06%，超过最强基线；在端到端多语OCR任务上，只替换识别模块就把F1从65.71%拉到80.89%，超过最好的超大模型，参数却少得多。它不是你明天就能装进手机的功能，但方向很明确：多语识别不必靠堆模型或堆参数，稀疏专家+合成数据就能做到又小又准。
📄 原文摘要(英文)
Multilingual scene text recognition (STR) remains challenging due to the scarcity of training data for most languages and the difficulty of serving diverse scripts within a single model. Existing solutions either deploy one recognizer per language, inflating cost and introducing error accumulation, or rely on massive vision-language models (VLMs) that are expensive and still inaccurate on many scripts. In this work, we pursue an all-in-one multilingual recognizer that is simpler than per-language experts, lighter than VLMs, and more accurate than both. First, we construct TextMuSS-10M, a large-scale synthetic scene text dataset spanning 10 scripts and 229 languages. It provides balanced and sufficient supervision where real data is unavailable. Second, we propose ScriptMoE, a script-aware Mixture-of-Experts (MoE) architecture. It shares a single visual encoder and replaces the dense decoder with a sparse MoE block, which consists of an image-level router dispatches each image to the top-2 script-aligned experts and a shared expert absorbs cross-script knowledge. Extensive experiments on our assembled TextMuSS-Bench (10 scripts, 10,899 images) show that ScriptMoE achieves the highest accuracy of 82.06%, outperforming the strongest STR baseline by 1.31%. On the CC-OCR end-to-end multilingual task, replacing only the recognizer in PP-OCRv5 with ScriptMoE lifts F1 score from 65.71% to 80.89%, slightly surpassing the best VLM (80.73%) at a fraction of the parameter count.