Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Selective Scene Text Removal (2309.00410v2)

Published 1 Sep 2023 in cs.CV and cs.LG

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.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (23)
  1. Scene text removal via cascaded text stroke detection and erasing. Computational Visual Media, 8(2):273–287, 2022.
  2. Synthetic data for text localisation in natural images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2315–2324, 2016.
  3. SwinTextSpotter: Scene text spotting via better synergy between text detection and text recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4593–4603, 2022.
  4. Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227, 2014.
  5. The surprisingly straightforward scene text removal method with gated attention and region of interest generation: A comprehensive prominent model analysis. In Proceedings of the European Conference on Computer Vision (ECCV), pages 457–472, 2022.
  6. Real-time scene text detection with differentiable binarization and adaptive scale fusion. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(1):919–931, 2022.
  7. EraseNet: end-to-end text removal in the wild. IEEE Transactions on Image Processing, 29:8760–8775, 2020.
  8. Scene text detection and recognition: the deep learning era. International Journal of Computer Vision, 129(1):161–184, 2021.
  9. Towards end-to-end unified scene text detection and layout analysis. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 1049–1059, 2022.
  10. Conditioned-U-Net: introducing a control mechanism in the u-net for multiple source separations. In Proceedings of the International Society for Music Information Retrieval Conference (ISMIR), pages 159–165, 2019.
  11. Scene text eraser. In Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), pages 832–837, 2017.
  12. U-Net: convolutional networks for biomedical image segmentation. In Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), pages 234–241, 2015.
  13. De-rendering stylized texts. In Proceedings of the IEEE International Conference on Computer Vision (ICCV), pages 1076–1085, 2021.
  14. Stroke-based scene text erasing using synthetic data for training. IEEE Transactions on Image Processing, 30:9306–9320, 2021.
  15. MTRNet: a generic scene text eraser. In Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), pages 39–44, 2019.
  16. MTRNet++: one-stage mask-based scene text eraser. Computer Vision and Image Understanding, 201:103066, 2020.
  17. PERT: a progressively region-based network for scene text removal. arXiv preprint arXiv:2106.13029, 2021.
  18. Editing text in the wild. In Proceedings of the ACM International Conference on Multimedia (ACMMM), pages 1500–1508, 2019.
  19. TextFuseNet: scene text detection with richer fused features. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pages 516–522, 2020.
  20. SynthTIGER: synthetic text image generator towards better text recognition models. In Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), pages 109–124, 2021.
  21. Erasing scene text with weak supervision. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 2238–2246, 2020.
  22. EnsNet: ensconce text in the wild. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pages 801–808, 2019.
  23. Text spotting transformers. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 9519–9528, 2022.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Hayato Mitani (3 papers)
  2. Akisato Kimura (32 papers)
  3. Seiichi Uchida (85 papers)
Citations (1)
View on Semantic Scholar