Zhengmi Tang , Tomo Miyazaki , Zhijie Wang , Yongsong Huang , Jonathan Pradana Mailoa , Shinichiro Omachi
{"title":"VQ-STE: Scene text erasing with mask refinement and vector-quantized texture dictionary","authors":"Zhengmi Tang , Tomo Miyazaki , Zhijie Wang , Yongsong Huang , Jonathan Pradana Mailoa , Shinichiro Omachi","doi":"10.1016/j.knosys.2025.113306","DOIUrl":null,"url":null,"abstract":"<div><div>Scene text erasing (STE), which aims to remove text from natural images and restore a plausible background, has been extensively researched in recent years. Most existing STE methods employ segment-then-erase pipelines, either explicitly or implicitly. However, these methods still face challenges, such as inaccurate text segmentation, difficulty in large text removal, and the shortage of training data. To address the first two issues, we present a scene-text-erasing network, VQ-STE, and to mitigate the third issue, we introduce a high-quality synthetic dataset, MixSyn. VQ-STE comprises a lightweight text Mask Refinement Network (MRN) and a Texture Dictionary-based Inpainting Network (TDIN). The MRN refines the bounding box-level text region mask, producing a high-recall stroke-level text mask by incorporating data augmentation and multiple loss functions. The TDIN erases large text regions by replacing distorted features with those from a pre-learned Texture Dictionary. Moreover, our generated MixSyn dataset offers greater diversity in background, text appearance, layout, and annotation compared to existing synthetic datasets. VQ-STE performs effectively in one or two-step settings, i.e., with or without additional text bounding box information. Experimental results demonstrate that VQ-STE outperforms existing one-step and two-step methods in quantitative and qualitative evaluations on the SCUT-EnsText dataset.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"315 ","pages":"Article 113306"},"PeriodicalIF":7.2000,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Knowledge-Based Systems","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0950705125003533","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
Abstract
Scene text erasing (STE), which aims to remove text from natural images and restore a plausible background, has been extensively researched in recent years. Most existing STE methods employ segment-then-erase pipelines, either explicitly or implicitly. However, these methods still face challenges, such as inaccurate text segmentation, difficulty in large text removal, and the shortage of training data. To address the first two issues, we present a scene-text-erasing network, VQ-STE, and to mitigate the third issue, we introduce a high-quality synthetic dataset, MixSyn. VQ-STE comprises a lightweight text Mask Refinement Network (MRN) and a Texture Dictionary-based Inpainting Network (TDIN). The MRN refines the bounding box-level text region mask, producing a high-recall stroke-level text mask by incorporating data augmentation and multiple loss functions. The TDIN erases large text regions by replacing distorted features with those from a pre-learned Texture Dictionary. Moreover, our generated MixSyn dataset offers greater diversity in background, text appearance, layout, and annotation compared to existing synthetic datasets. VQ-STE performs effectively in one or two-step settings, i.e., with or without additional text bounding box information. Experimental results demonstrate that VQ-STE outperforms existing one-step and two-step methods in quantitative and qualitative evaluations on the SCUT-EnsText dataset.
期刊介绍:
Knowledge-Based Systems, an international and interdisciplinary journal in artificial intelligence, publishes original, innovative, and creative research results in the field. It focuses on knowledge-based and other artificial intelligence techniques-based systems. The journal aims to support human prediction and decision-making through data science and computation techniques, provide a balanced coverage of theory and practical study, and encourage the development and implementation of knowledge-based intelligence models, methods, systems, and software tools. Applications in business, government, education, engineering, and healthcare are emphasized.