← 研踪 PaperTrailCVF · CVPR 2026:cvf:da0d89df0195f0c56b71f204e555a9a2 · 记录 #1
Restore Text First, Enhance Image Later: Two-Stage Scene Text Image Super-Resolution with Glyph Structure Guidance
Luo, MinxingFan, LinlongWang, QiushiWu, GeLuo, YiyanYu, YuhangChen, JinweiWang, YaxingFan, QingnanYang, Jian 来源日期(仅到年份) 2026
来源记录日期 2026
雷达观测 2026-11-01 23:50
摘要
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.
论文发现出处
这些页面提供论文线索,不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化,不是作者修订号。来源日期仅到月份或年份时,按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
Restore Text First, Enhance Image Later: Two-Stage Scene Text Image Super-Resolution with Glyph Structure Guidance
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.
查看此版本解读 →查看此版本原文 ↗