GLYPH-SR: Can We Achieve Both High-Quality Image Super-Resolution and High-Fidelity Text Recovery via VLM-Guided Latent Diffusion Model?

ICLR 2026 Conference Submission8495 Authors

Keywords: Diffusion Models, Optical Character Recognition, Scene Image Restoration, Super-Resolution, Vision–Language Models

Abstract: Image super‑resolution (SR) is fundamental to many vision systems—from surveillance and autonomy to document analysis and retail analytics—because recovering high‑frequency details, especially scene-text, enables reliable downstream perception. scene-text, i.e., text embedded in natural images such as signs, product labels, and storefronts, often carries the most actionable information; when characters are blurred or hallucinated, optical character recognition (OCR) and subsequent decisions fail even if the rest of the image appears sharp. Yet previous SR research has often been tuned to distortion (PSNR/SSIM) or learned perceptual metrics (LPIPS, MANIQA, CLIP‑IQA, MUSIQ) that are largely insensitive to character-level errors. Furthermore, studies that do address text SR often focus on simplified benchmarks with isolated characters, overlooking the challenges of text within complex natural scenes. As a result, scene-text is effectively treated as generic texture. For SR to be effective in practical deployments, it is therefore essential to explicitly optimize for both text legibility and perceptual quality. We present GLYPH‑SR, a vision–language‑guided diffusion framework that aims to achieve both objectives jointly. GLYPH-SR utilizes a Text-SR Fusion ControlNet (TS-ControlNet) guided by OCR data, and a ping-pong scheduler that alternates between text- and scene-centric guidance. To enable targeted text restoration, we train these components on a synthetic corpus while keeping the main SR branch frozen. Across SVT, SCUT‑CTW1500, and CUTE80 at ×4 and ×8, GLYPH‑SR improves OCR F1 score by up to +15.18 percentage points over diffusion/GAN baselines (SVT ×8, OpenOCR) while maintaining competitive MANIQA, CLIP‑IQA, and MUSIQ. GLYPH‑SR is designed to satisfy both objectives simultaneously—high readability and high visual realism—delivering SR that looks right and reads right. We provide code, pretrained models, the synthetic corpus with generation scripts, and an evaluation suite to support reproducibility.

Primary Area: generative models

Submission Number: 8495