Research map / Image generation / Image restoration
EnsNet: Ensconce Text in the Wild
Shuaitao Zhang, Yuliang Liu, Lianwen Jin, Yaoxiong Huang, Songxuan Lai
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 lateral connections to the FCN baseline (ablation) | FCN baseline · Synthetic | ℓ₂ error: 0.4256 -> 0.0627 | Improved |
| Add refined loss to the FCN with lateral connections (ablation) | FCN with lateral connections · Synthetic | PSNR: 24.83 -> 30.23 | Improved |
| Add the local-aware text discriminator (ablation) | FCN with lateral connections and refined loss · Synthetic | PSNR: 30.23 -> 37.36 | Improved |
| Use EnsNet rather than Pix2Pix | Scene text erasure · Synthetic | PSNR: 25.60 -> 37.36 | Improved |
| Use EnsNet rather than Scene text eraser | Scene text erasure · Synthetic | PSNR: 14.68 -> 37.36 | Improved |
Later papers that compared with this method
1 later accepted paper reports EnsNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- The Surprisingly Straightforward Scene Text Removal Method with Gated Attention and Region of Interest Generation: A Comprehensive Prominent Model Analysis (ECCV 2022 · 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
- The Surprisingly Straightforward Scene Text Removal Method with Gated Attention and Region of Interest Generation: A Comprehensive Prominent Model Analysis (ECCV 2022 · similarity 0.87)
- ViTEraser: Harnessing the Power of Vision Transformers for Scene Text Removal with SegMIM Pretraining (AAAI 2024 · similarity 0.85)
- DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement (TPAMI 2020 · similarity 0.84)
- Don’t Forget Me: Accurate Background Recovery for Text Removal via Modeling Local-Global Context (ECCV 2022 · similarity 0.84)
- DuMo: Dual Encoder Modulation Network for Precise Concept Erasure (AAAI 2025 · similarity 0.83)
- TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control (NeurIPS 2024 · similarity 0.82)
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.
