Research map / Image generation / Text-to-image diffusion
TripleFDS: Triple Feature Disentanglement and Synthesis for Scene Text Editing
Yuchen Bao, Yiting Wang, Wenjian Huang, Haowei Wang, Shen Chen, Taiping Yao, Shouhong Ding, Jianguo Zhang
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 feature remapping strategy (RS) to baseline reconstruction losses (ablation) | TripleFDS · ScenePair | FID: 49.31 -> 46.56 | Improved |
| add inter-group contrastive loss Linter (ablation) | TripleFDS · ScenePair | ACC: 92.24 -> 93.14 | Improved |
| add inter-group contrastive loss Linter (ablation) | TripleFDS · ScenePair | FID: 46.56 -> 47.08 | Hurt |
| add intra-sample orthogonality loss Lintra (ablation) | TripleFDS · ScenePair | FID: 47.08 -> 46.40 | Improved |
| add intra-sample orthogonality loss Lintra (ablation) | TripleFDS · ScenePair | SSIM: 44.73 -> 44.54 | Hurt |
| use unbalanced SCB group config (4,2,4,2) instead of (8,2,2,2) (ablation) | TripleFDS · ScenePair | FID: 46.40 -> 49.48 | Hurt |
| use more groups with two elements per dimension (8,2,2,2) instead of (1,4,4,4) (ablation) | TripleFDS · ScenePair | ACC: 93.13 -> 93.58 | Improved |
| TripleFDS vs TextCtrl on real-scene background realism | TripleFDS · ScenePair | FID: 43.78 vs 46.40 | Hurt |
| TripleFDS vs RS-STE on pixel error in first column group | TripleFDS · Tamper-Syn2k (first column group) | MSE: 1.17 vs 1.26 | Hurt |
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.
- TextCtrl — TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control (NeurIPS 2024) · better on 5 of 6 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
- ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing (NeurIPS 2026 · similarity 0.87)
- ParallelEdits: Efficient Multi-Aspect Text-Driven Image Editing with Attention Grouping (NeurIPS 2024 · similarity 0.87)
- TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control (NeurIPS 2024 · similarity 0.86)
- DreamText: High Fidelity Scene Text Synthesis (CVPR 2025 · similarity 0.86)
- TextNeRF: A Novel Scene-Text Image Synthesis Method based on Neural Radiance Fields (CVPR 2024 · similarity 0.85)
- Disentangled 3D Scene Generation with Layout Learning (ICML 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.
