先复原文本、后增强图像：字形结构引导的两阶段场景文本图像超分辨率
Restore Text First, Enhance Image Later: Two-Stage Scene Text Image Super-Resolution with Glyph Structure Guidance
把「先恢复字形结构、再用结构引导整图超分」的解耦范式引入文本图像复原，可直接复用于场景文本识别前的预处理，或迁移到文档、车牌等含强结构先验的低质图像增强任务。
原文依据 it first reconstructs precise text structures and uses them to guide full-image super-resolution
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论当前的图像超分辨率方法在自然图像上表现强劲，但会使文本发生畸变，从而在图像质量与文本可读性之间形成根本性的权衡。为解决这一问题，本文提出 TIGER（文本-图像引导超分辨率），一种新颖的两阶段框架，通过「先文本、后图像」的范式打破该权衡。TIGER 将字形复原与图像增强显式解耦：它首先重建精确的文本结构，并利用这些结构引导全图超分辨率，从而同时保证高保真度与可读性。为支持全面的训练与评测，本文提出 UZ-ST（UltraZoom-ST）数据集，这是首个具有极端缩放的中文场景文本数据集。大量实验表明，TIGER 取得了最优性能，同时提升了可读性与图像质量。
英文原文摘要 854 字符
Current image super-resolution methods show strong performance on natural images but distort text, creating a fundamental trade-off between image quality and textual readability. To address this, we introduce **TIGER** (**T**ext-**I**mage **G**uided sup**E**r-**R**esolution), a novel two-stage framework that breaks this trade-off through a *"text-first, image-later"* paradigm. TIGER explicitly decouples glyph restoration from image enhancement: it first reconstructs precise text structures and uses them to guide full-image super-resolution. This ensures high fidelity and readability. To support comprehensive training and evaluation, we present the UZ-ST (UltraZoom-ST) dataset, the first Chinese scene text dataset with extreme zoom. Extensive experiments show TIGER achieves state-of-the-art performance, enhancing readability and image quality.