ClearText-Video: A Large-Scale Text-Centric Video Dataset Bridging Video Restoration and Scene-Text Enhancement

2026-08-28

AI Summary

研究通过构建ClearText-Video数据集，解决多模态大语言模型在处理真实世界文本中心视频时的质量敏感问题，涵盖视频恢复与场景文本增强任务。

Abstract

Multimodal Large Language Models (MLLMs) have recently made strong progress in visual--linguistic understanding. However, their performance on text-centric video reasoning remains highly sensitive to input quality. Real-world user-provided videos often contain motion blur, compression artifacts, noise, and low-resolution text, which impair reliable text reading and downstream reasoning. Whether MLLMs can robustly read and reason about real-world scene text under diverse quality conditions remains a fundamental open question. We introduce ClearText-Video (CTVid), a large-scale, scene-text-aware benchmark for studying text-centric video understanding under controlled quality variation. CTVid contains 4,639 real-world text-rich egocentric videos, 550K+ frames, 1.6M human-verified scene-text annotations, and 220K+ spatial/temporal question--answer pairs in Chinese and English. For each high-quality video, CTVid provides content-matched Degraded-Quality and Restored-Quality variants, supporting two task families: Text-Centric Video Restoration and Multi-Quality VideoQA. We evaluate 18 representative restoration methods and 16 state-of-the-art MLLMs on CTVid. The results show that visual enhancement does not guarantee textual fidelity or downstream reasoning gains: blur is more damaging than low resolution, restored videos can alter the textual evidence used by MLLMs, and OCR-only pipelines remain far below direct multimodal reasoning. CTVid exposes the gap between video restoration and text-grounded understanding, providing a rigorous foundation for restoration-aware, quality-robust text-centric video systems.

Problem

• Multimodal Large Language Models
• Text-Centric Video Reasoning
• Input Quality
• Scene-Text Enhancement
• Video Restoration

Innovation

• ClearText-Video
• Scene-Text Enhancement
• Text-Centric Video Restoration
• Multi-Quality VideoQA
• Multimodal Large Language Models