Research map / Label-efficient and robust learning / Recognition and long-tail
Axis-Aligned Document Dewarping
Chaoyun Wang, I-Chao Shen, Takeo Igarashi, Caigui Jiang
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 axis-aligned geometric constraint loss (AL) (ablation) | UVDoc-based dewarping network · DocUNet benchmark | AAD: 0.124 -> 0.105 | Improved |
| add AL (ablation) | UVDoc-based dewarping network · DIR300 benchmark | AAD: 0.100 -> 0.076 | Improved |
| add axis alignment preprocessing (AP) (ablation) | UVDoc-based dewarping network · DocUNet benchmark | AAD: 0.124 -> 0.120 | No clear effect |
| add AP (ablation) | UVDoc-based dewarping network · DIR300 benchmark | AAD: 0.100 -> 0.069 | Improved |
| add AL and AP together (ablation) | UVDoc-based dewarping network · DocUNet benchmark | AAD: 0.124 -> 0.099 | Improved |
| add AL and AP together (ablation) | UVDoc-based dewarping network · DIR300 benchmark | CER: 0.243 -> 0.132 | Improved |
| add AL (ablation) | UVDoc-based dewarping network · DocUNet benchmark | CER: 0.167 -> 0.183 | Hurt |
| add AL (ablation) | UVDoc-based dewarping network · DIR300 benchmark | CER: 0.243 -> 0.206 | Improved |
| add AP (ablation) | UVDoc-based dewarping network · DIR300 benchmark | LD: 7.691 -> 4.303 | Improved |
| use full model instead of UVDoc | document dewarping · DocUNet benchmark | MS-SSIM: 0.545 vs 0.543 | No clear effect |
Closest papers by meaning
- D2Dewarp: Dual Dimensions Geometric Representation Learning Based Document Image Dewarping (CVPR 2026 · similarity 0.90)
- M2Doc: A Multi-Modal Fusion Approach for Document Layout Analysis (AAAI 2024 · similarity 0.82)
- RoDLA: Benchmarking the Robustness of Document Layout Analysis Models (CVPR 2024 · similarity 0.81)
- DocFormerv2: Local Features for Document Understanding (AAAI 2024 · similarity 0.81)
- DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks (CVPR 2024 · similarity 0.81)
- Angle Domain Guidance: Latent Diffusion Requires Rotation Rather Than Extrapolation (ICML 2025 · similarity 0.81)
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.
