Research map / Image generation / Text-to-image diffusion
The Surprisingly Straightforward Scene Text Removal Method with Gated Attention and Region of Interest Generation: A Comprehensive Prominent Model Analysis
Hyeonsu Lee, Chankyu Choi
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add text box mask input to EnsNet (ablation) | EnsNet · SCUT-EnsText (text region pasted) | PSNR: 32.99 -> 37.28 | Improved |
| add simple attention (ablation) | BaseLine · SCUT-EnsText (text region pasted) | PSNR: 37.28 -> 37.24 | No clear effect |
| add simple attention (ablation) | BaseLine · SCUT-EnsText (text region pasted) | Detection F-score: 43.6 -> 45.1 | Hurt |
| add text stroke region attention (TSRA) (ablation) | BaseLine · SCUT-EnsText (text region pasted) | PSNR: 37.28 -> 38.06 | Improved |
| add text stroke region attention (TSRA) (ablation) | BaseLine · SCUT-EnsText (text region pasted) | Detection F-score: 43.6 -> 30.4 | Improved |
| add stroke surrounding region attention (TSSRA) (ablation) | BaseLine · SCUT-EnsText (text region pasted) | PSNR: 37.28 -> 38.45 | Improved |
| add stroke surrounding region attention (TSSRA) (ablation) | BaseLine · SCUT-EnsText (text region pasted) | Detection F-score: 43.6 -> 10.5 | Improved |
| add gated attention (GA) (ablation) | BaseLine · SCUT-EnsText (text region pasted) | PSNR: 37.28 -> 38.82 | Improved |
| add gated attention (GA) (ablation) | BaseLine · SCUT-EnsText (text region pasted) | Detection F-score: 43.6 -> 6.9 | Improved |
| add region-of-interest generation (RoIG) (ablation) | BaseLine · SCUT-EnsText (text region pasted) | PSNR: 37.28 -> 40.82 | Improved |
| add region-of-interest generation (RoIG) (ablation) | BaseLine · SCUT-EnsText (text region pasted) | Detection F-score: 43.6 -> 5.6 | Improved |
| add RoIG on top of GA (ablation) | BaseLine + GA · SCUT-EnsText (text region pasted) | PSNR: 38.82 -> 41.37 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- EnsNet — EnsNet: Ensconce Text in the Wild (AAAI 2019) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining (AAAI 2024 · similarity 0.90)
- Revisiting Tampered Scene Text Detection in the Era of Generative AI (AAAI 2025 · similarity 0.88)
- OTE: Exploring Accurate Scene Text Recognition Using One Token (CVPR 2024 · similarity 0.86)
- Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing (NeurIPS 2024 · similarity 0.86)
- One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework (ICML 2025 · similarity 0.85)
- Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model (AAAI 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
