ReasonText 基准揭示图像超分辨率在退化文本上的推理盲区
Reading the Unreadable: Text-Aware Image Super-Resolution Needs Reasoning
这项研究问了个人们没细想的问题：超分模型修不清文字，是不是缺了推理能力。他们做的 ReasonText 基准把问题量化了，RTC 插件不用重新训练就能接在现有模型上提升文字修复，做图像修复或 OCR 相关工作的开发者可以直接借鉴这套思路。
一篇 arXiv 论文提出文本感知图像超分辨率（TAISR）不能只靠视觉修复：严重退化的文字无法从局部视觉证据中辨认，需要结合上下文与先验知识进行推理。作者构建了人工标注的 ReasonText 基准，区分需要推理的文本与局部可恢复的文本，并设计了 GTTCA 指标，在不依赖文本检测的情况下衡量文本修复质量。对 12 个近期超分模型的评测显示，所有模型在需要推理的文本上出现一致的明显性能下降。
论文给出两个关键观察：给 text-conditioned SR 模型提供 ground-truth 文本时，修复效果显著提升；同时 MLLM 能够通过推理读出低分辨率图像中的退化文字。据此提出免训练插件 RTC，用外部 MLLM 推断退化文本并生成 caption，再喂给 text-conditioned SR 模型。RTC 对全部 6 个被评测的 text-conditioned SR 模型都有提升，在推理型文本上尤其明显。
Reading the Unreadable: Text-Aware Image Super-Resolution Needs Reasoning
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.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：ReasonText、GTTCA、MLLM、超分辨率，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.AI」（@Jaeseong Lee, Jinwoo Kim, Jinho Jeong, Seon Joo Kim），经 AITOP 多维评分管线结构化提炼。