paper-with-me

Papers

Recognition-Guided Diffusion Model for Scene Text Image Super-Resolution

2023-11-22 · Yuxuan Zhou, Liangcai Gao, Zhi Tang, Baole Wei

Scene Text Image Super-Resolution (STISR) aims to enhance the resolution and legibility of text within low-resolution (LR) images, consequently elevating recognition accuracy in Scene Text Recognition (STR). Previous methods predominantly employ discriminative Convolutional Neural Networks (CNNs) augmented with diverse forms of text guidance to address this issue. Nevertheless, they remain deficient when confronted with severely blurred images, due to their insufficient generation capability when little structural or semantic information can be extracted from original images. Therefore, we introduce RGDiffSR, a Recognition-Guided Diffusion model for scene text image Super-Resolution, which exhibits great generative diversity and fidelity even in challenging scenarios. Moreover, we propose a Recognition-Guided Denoising Network, to guide the diffusion model generating LR-consistent results through succinct semantic guidance. Experiments on the TextZoom dataset demonstrate the superiority of RGDiffSR over prior state-of-the-art methods in both text recognition accuracy and image fidelity.

📄 PDF Abstract BibTeX arXiv:2311.13317

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingDiversityImage Super-ResolutionScene Text RecognitionSuper-Resolution

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

DiffusionSTR: Diffusion Model for Scene Text Recognition

2023-06-29 · Masato Fujitake

This paper presents Diffusion Model for Scene Text Recognition (DiffusionSTR), an end-to-end text recognition framework using diffusion models for recognizing text in the wild. While existing studies have viewed the scen…

Image to textmodelScene Text Recognition

Text Image Inpainting via Global Structure-Guided Diffusion Models

2024-01-26 · Shipeng Zhu, Pengfei Fang, Chenjie Zhu, Zuoyan Zhao 외

Real-world text can be damaged by corrosion issues caused by environmental or human factors, which hinder the preservation of the complete styles of texts, e.g., texture and structure. These corrosion issues, such as gra…

Image InpaintingScene Text Recognition

GLYPH-SR: Can We Achieve Both High-Quality Image Super-Resolution and High-Fidelity Text Recovery via VLM-guided Latent Diffusion Model?

2025-10-30 · Mingyu Sung, Seungjae Ham, Kangwoo Kim, Yeokyoung Yoon 외 arxiv

Image super-resolution(SR) is fundamental to many vision system-from surveillance and autonomy to document analysis and retail analytics-because recovering high-frequency details, especially scene-text, enables reliable …

Image Super-Resolution

On Manipulating Scene Text in the Wild with Diffusion Models

2023-11-01 · Joshua Santoso, Christian Simon, Williem Pao

Diffusion models have gained attention for image editing yielding impressive results in text-to-image tasks. On the downside, one might notice that generated images of stable diffusion models suffer from deteriorated det…

Optical Character RecognitionOptical Character Recognition (OCR)Scene Text Editing

Text Prior Guided Scene Text Image Super-resolution

2021-06-29 · jianqi ma, Shi Guo, Lei Zhang

Scene text image super-resolution (STISR) aims to improve the resolution and visual quality of low-resolution (LR) scene text images, and consequently boost the performance of text recognition. However, most of existing …

Image Super-ResolutionSuper-Resolution