cs.CVNov 11, 2026

Reading the Unreadable: Text-Aware Image Super-Resolution Needs Reasoning

Authors: Jaeseong Lee, Jinwoo Kim, Jinho Jeong, Seon Joo Kim

Organizations: CIPLAB, Yonsei University

Abstract

Text-aware image super-resolution (TAISR) aims to recover high-resolution images from low-resolution inputs while preserving textual content. Existing methods treat this as a visual restoration problem, yet severely degraded text often cannot be read from local visual evidence alone. Humans instead read it by reasoning over image context, logical patterns, and prior knowledge. This raises a fundamental question: Does TAISR need reasoning? To answer this, we introduce two diagnostic tools. The first, ReasonText, is a human-curated benchmark that separates reasoning-required text from locally recoverable text. The second, Ground-Truth Text-Crop Accuracy (GTTCA), is a recognition-based metric that measures text restoration quality without text detection errors. Evaluating twelve recent super-resolution (SR) models, we find a consistent and substantial performance drop on reasoning-required text, revealing a systematic blind spot. Two observations point to a remedy. One is that text-conditioned SR models restore text substantially better when given ground-truth text. The other is that multimodal large language models (MLLMs) can read degraded text in low-resolution images through reasoning. We therefore propose Reasoning Transfer via Captioning (RTC), a training-free plug-in that uses an external MLLM to infer the degraded text and feeds the resulting caption to a text-conditioned SR model. RTC consistently improves all six text-conditioned SR models we evaluate, especially on reasoning-required text. Surprisingly, a real-world SR model with RTC can even outperform the TAISR model with RTC, suggesting that reasoning should be a core design axis for future TAISR.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. TOLA: Text-aware One-Step Latent Adaptation for Diffusion-based Text Image Super-Resolution

    Sep 24, 2026Yike Xu, Yue Shi, Yong Guo +1Diffusion Models for Image RestorationImage Super-Resolution

  2. DualTSR: Unified Dual-Diffusion Transformer for Scene Text Image Super-Resolution

    Mar 15, 2026Axi Niu, Kang Zhang, Qingsen Yan +3Discrete Diffusion SamplingImage Super-Resolution

  3. TGSR: Text-Grounded Diffusion for Faithful Image Super-Resolution

    Oct 9, 2026Zhiming Hu, Ran Zhang, Angela Ye +7Image Super-ResolutionDiffusion Models for Image Restoration