Research map / Image generation / Text-to-image diffusion
SwapText: Image Based Texts Transfer in Scenes
Qiangpeng Yang, Jun Huang, Wei Lin
Check 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 |
|---|---|---|---|
| Use SwapText (multi) instead of SRNet | Synthetic text swapping · Synthetic test dataset, English and Chinese | PSNR: 14.91 -> 16.04; 14.77 -> 15.46 | Improved |
| Add CSTN to the full method (ablation) | SwapText · Synthetic test dataset, English and Chinese | PSNR: 15.22 -> 16.04; 14.98 -> 15.46 | Improved |
| Add self-attention to combine content and style features (ablation) | SwapText · Synthetic test dataset, English and Chinese | PSNR: 15.31 -> 16.04; 15.02 -> 15.46 | Improved |
| Use multi-level rather than single-level self-attention (ablation) | SwapText · Synthetic test dataset, English and Chinese | SSIM: 0.6523 -> 0.6621; 0.6112 -> 0.6189 | Improved |
| Add dilated convolution to background completion (ablation) | SwapText · Synthetic test dataset, English and Chinese | PSNR: 15.23 -> 16.04; 15.15 -> 15.46 | Improved |
| Use SwapText instead of SRNet for text detection on generated data | Text detection datasets · IC13 and IC15 | F-measure: 76.1 -> 78.4; 78.1 -> 80.2 | Improved |
Later papers that compared with this method
2 later accepted papers report SwapText as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Exploring Stroke-Level Modifications for Scene Text Editing (AAAI 2023 · better on 5 of 5 shared results)
- TextStyleBrush: Transfer of Text Aesthetics From a Single Example (TPAMI 2023 · better on 1 of 1 shared result)
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
- DreamText: High Fidelity Scene Text Synthesis (CVPR 2025 · similarity 0.87)
- TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation (ICML 2025 · similarity 0.86)
- Brush Your Text: Synthesize Any Scene Text on Images via Diffusion Model (AAAI 2024 · similarity 0.86)
- Layout-Agnostic Scene Text Image Synthesis with Diffusion Models (CVPR 2024 · similarity 0.86)
- TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control (NeurIPS 2024 · similarity 0.85)
- AnyText: Multilingual Visual Text Generation and Editing (ICLR 2024 · similarity 0.84)
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.
