Saved in:
Bibliographic Details
Main Authors: Hu, Qiming, Fan, Linlong, Luo, Yiyan, Yu, Yuhang, Guo, Xiaojie, Fan, Qingnan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.04641
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918046333927424
author Hu, Qiming
Fan, Linlong
Luo, Yiyan
Yu, Yuhang
Guo, Xiaojie
Fan, Qingnan
author_facet Hu, Qiming
Fan, Linlong
Luo, Yiyan
Yu, Yuhang
Guo, Xiaojie
Fan, Qingnan
contents The introduction of generative models has significantly advanced image super-resolution (SR) in handling real-world degradations. However, they often incur fidelity-related issues, particularly distorting textual structures. In this paper, we introduce a novel diffusion-based SR framework, namely TADiSR, which integrates text-aware attention and joint segmentation decoders to recover not only natural details but also the structural fidelity of text regions in degraded real-world images. Moreover, we propose a complete pipeline for synthesizing high-quality images with fine-grained full-image text masks, combining realistic foreground text regions with detailed background content. Extensive experiments demonstrate that our approach substantially enhances text legibility in super-resolved images, achieving state-of-the-art performance across multiple evaluation metrics and exhibiting strong generalization to real-world scenarios. Our code is available at \href{https://github.com/mingcv/TADiSR}{here}.
format Preprint
id arxiv_https___arxiv_org_abs_2506_04641
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Text-Aware Real-World Image Super-Resolution via Diffusion Model with Joint Segmentation Decoders
Hu, Qiming
Fan, Linlong
Luo, Yiyan
Yu, Yuhang
Guo, Xiaojie
Fan, Qingnan
Computer Vision and Pattern Recognition
The introduction of generative models has significantly advanced image super-resolution (SR) in handling real-world degradations. However, they often incur fidelity-related issues, particularly distorting textual structures. In this paper, we introduce a novel diffusion-based SR framework, namely TADiSR, which integrates text-aware attention and joint segmentation decoders to recover not only natural details but also the structural fidelity of text regions in degraded real-world images. Moreover, we propose a complete pipeline for synthesizing high-quality images with fine-grained full-image text masks, combining realistic foreground text regions with detailed background content. Extensive experiments demonstrate that our approach substantially enhances text legibility in super-resolved images, achieving state-of-the-art performance across multiple evaluation metrics and exhibiting strong generalization to real-world scenarios. Our code is available at \href{https://github.com/mingcv/TADiSR}{here}.
title Text-Aware Real-World Image Super-Resolution via Diffusion Model with Joint Segmentation Decoders
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.04641