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

arXiv: https://arxiv.org/abs/2608.28784 · HTML: https://mlsanity.com/paper/2608.28784/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 60 of its 75 references that are in the map.
- First posted on arXiv 28 Aug 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 30 of 60)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Simple Baselines for Image Restoration](https://mlsanity.com/paper/2204.04676/) (2022)
- [VILA: On Pre-training for Visual Language Models](https://mlsanity.com/paper/2312.07533/) (2023)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models](https://mlsanity.com/paper/2407.07895/) (2024)
- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs](https://mlsanity.com/paper/2503.01743/) (2025)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://mlsanity.com/paper/2307.06942/) (2023)
- [TVQA: Localized, Compositional Video Question Answering](https://mlsanity.com/paper/1809.01696/) (2018)
- [Kimi-VL Technical Report](https://mlsanity.com/paper/2504.07491/) (2025)
- [BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment](https://mlsanity.com/paper/2104.13371/) (2021)
- [Scene Text Visual Question Answering](https://mlsanity.com/paper/1905.13648/) (2019)
- [Rethinking Coarse-to-Fine Approach in Single Image Deblurring](https://mlsanity.com/paper/2108.05054/) (2021)
- [SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution](https://mlsanity.com/paper/2311.16518/) (2023)

## Abstract (arXiv)

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.