TEXTS-Diff: TEXTS-Aware Diffusion Model for Real-World Text Image Super-Resolution

TL;DR

TEXTS-Diff introduces a novel diffusion-based approach and a large-scale real-world dataset to significantly improve text image super-resolution, restoring both background and textual details with high fidelity.

Contribution

The paper presents a new TEXTS-Aware Diffusion Model and the Real-Texts dataset, addressing data scarcity and improving text and background restoration in real-world scenarios.

Findings

Achieves state-of-the-art super-resolution performance.

Demonstrates superior generalization in complex scenes.

Effectively reduces distortions and hallucinations in text regions.

Abstract

Real-world text image super-resolution aims to restore overall visual quality and text legibility in images suffering from diverse degradations and text distortions. However, the scarcity of text image data in existing datasets results in poor performance on text regions. In addition, datasets consisting of isolated text samples limit the quality of background reconstruction. To address these limitations, we construct Real-Texts, a large-scale, high-quality dataset collected from real-world images, which covers diverse scenarios and contains natural text instances in both Chinese and English. Additionally, we propose the TEXTS-Aware Diffusion Model (TEXTS-Diff) to achieve high-quality generation in both background and textual regions. This approach leverages abstract concepts to improve the understanding of textual elements within visual scenes and concrete text regions to enhance textual details. It mitigates distortions and hallucination artifacts commonly observed in text regions, while preserving high-quality visual scene fidelity. Extensive experiments demonstrate that our method achieves state-of-the-art performance across multiple evaluation metrics, exhibiting superior generalization ability and text restoration accuracy in complex scenarios. All the code, model, and dataset will be released.