Restore Text First, Enhance Image Later: Two-Stage Scene Text Image Super-Resolution with Glyph Structure Guidance
This addresses the trade-off between image quality and textual readability in scene text super-resolution, which is important for applications like document digitization and augmented reality, though it is an incremental improvement over existing methods.
The paper tackled the problem of generative super-resolution methods distorting text in images, introducing TIGER, a two-stage framework that first restores text structures and then enhances the full image, achieving state-of-the-art performance with improved readability and image quality.
Current generative 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 \textbf{TIGER} (\textbf{T}ext-\textbf{I}mage \textbf{G}uided sup\textbf{E}r-\textbf{R}esolution), a novel two-stage framework that breaks this trade-off through a \textit{"text-first, image-later"} paradigm. \textbf{TIGER} explicitly decouples glyph restoration from image enhancement: it first reconstructs precise text structures and then uses them to guide subsequent full-image super-resolution. This glyph-to-image guidance ensures both high fidelity and visual consistency. To support comprehensive training and evaluation, we also contribute the \textbf{UltraZoom-ST} (UltraZoom-Scene Text), the first scene text dataset with extreme zoom (\textbf{$\times$14.29}). Extensive experiments show that \textbf{TIGER} achieves \textbf{state-of-the-art} performance, enhancing readability while preserving overall image quality.