Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.02787 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914072561188864 |
|---|---|
| author | Zdenek, Jan Shimoda, Wataru Yamaguchi, Kota |
| author_facet | Zdenek, Jan Shimoda, Wataru Yamaguchi, Kota |
| contents | Text removal is a crucial task in computer vision with applications such as privacy preservation, image editing, and media reuse. While existing research has primarily focused on scene text removal in natural images, limitations in current datasets hinder out-of-domain generalization or accurate evaluation. In particular, widely used benchmarks such as SCUT-EnsText suffer from ground truth artifacts due to manual editing, overly simplistic text backgrounds, and evaluation metrics that do not capture the quality of generated results. To address these issues, we introduce an approach to synthesizing a text removal benchmark applicable to domains other than scene texts. Our dataset features text rendered on complex backgrounds using object-aware placement and vision-language model-generated content, ensuring clean ground truth and challenging text removal scenarios. The dataset is available at https://huggingface.co/datasets/cyberagent/OTR . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_02787 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OTR: Synthesizing Overlay Text Dataset for Text Removal Zdenek, Jan Shimoda, Wataru Yamaguchi, Kota Computer Vision and Pattern Recognition Text removal is a crucial task in computer vision with applications such as privacy preservation, image editing, and media reuse. While existing research has primarily focused on scene text removal in natural images, limitations in current datasets hinder out-of-domain generalization or accurate evaluation. In particular, widely used benchmarks such as SCUT-EnsText suffer from ground truth artifacts due to manual editing, overly simplistic text backgrounds, and evaluation metrics that do not capture the quality of generated results. To address these issues, we introduce an approach to synthesizing a text removal benchmark applicable to domains other than scene texts. Our dataset features text rendered on complex backgrounds using object-aware placement and vision-language model-generated content, ensuring clean ground truth and challenging text removal scenarios. The dataset is available at https://huggingface.co/datasets/cyberagent/OTR . |
| title | OTR: Synthesizing Overlay Text Dataset for Text Removal |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.02787 |