Selective Scene Text Removal

Hayato Mitani, Akisato Kimura, Seiichi Uchida
9/1/2023
cs.CVcs.LG

No official code found. Best implementation: mitanihayato/Selective-Scene-Text-Removal (9 stars, last commit 2023-11-25).

Abstract

Scene text removal (STR) is the image transformation task to remove text regions in scene images. The conventional STR methods remove all scene text. This means that the existing methods cannot select text to be removed. In this paper, we propose a novel task setting named selective scene text removal (SSTR) that removes only target words specified by the user. Although SSTR is a more complex task than STR, the proposed multi-module structure enables efficient training for SSTR. Experimental results show that the proposed method can remove target words as expected.

View on arXivView PDF

Code Implementations(1)

mitanihayato/Selective-Scene-Text-RemovalCommunity100%

BMVC 2023: Selective Scene Text Removal

90PythonSep 19, 20232 years agoNOASSERTION
bmvc2023scene-text-removaltext-removal

Similar Papers

FETNet: Feature Erasing and Transferring Network for Scene Text Removal

86% match1 repo352023

PSSTRNet: Progressive Segmentation-guided Scene Text Removal Network

83% match1 repo132023

Leveraging Text Localization for Scene Text Removal via Text-aware Masked Image Modeling

81% match1 repo132024

Progressive Scene Text Erasing with Self-Supervision

81% match2022

ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining

80% match1 repo682023

Towards Training-Free Scene Text Editing

78% match2026

Cite this paper

@article{mitani2023selective,
  title  = {Selective Scene Text Removal},
  author = {Hayato Mitani and Akisato Kimura and Seiichi Uchida},
  year   = {2023},
  eprint = {2309.00410},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2309.00410v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2309.00410.svg)](https://codeofpaper.com/paper/2309.00410)

Discussion