Research map / Image generation / Image restoration
Revisiting Document Image Dewarping by Grid Regularization
Xiangwei Jiang, Rujiao Long, Nan Xue, Zhibo Yang, Cong Yao, Gui-Song Xia
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 grid regularization with text-line and boundary constraints instead of learned dense deformation | Document dewarping · DocUNet benchmark | CER: 0.3001 (0.14) -> 0.2068 (0.141) | Improved |
| use grid regularization with text-line and boundary constraints instead of learned dense deformation | Document dewarping · DocUNet benchmark | ED: 1288.60 -> 896.48 | Improved |
| use grid regularization with text-line and boundary constraints instead of learned dense deformation | Document dewarping · DocUNet benchmark | MS-SSIM: 0.4879 -> 0.4922 | Improved |
| use grid regularization with text-line and boundary constraints instead of learned dense deformation | Document dewarping · DocUNet benchmark | LD: 8.50 -> 9.36 | Mixed |
| add text-line constraints to boundary constraints (ablation) | Grid regularization dewarping · DocUNet benchmark | CER: 0.3511 (0.183) -> 0.2081 (0.142) | Improved |
| add text-line constraints to boundary constraints (ablation) | Grid regularization dewarping · DocUNet benchmark | ED: 1513.04 -> 908.84 | Improved |
| add vertical-line constraints to boundary and text-line constraints (ablation) | Grid regularization dewarping · DocUNet benchmark | CER: 0.2081 (0.142) -> 0.2068 (0.141) | Improved |
| add vertical-line constraints to boundary and text-line constraints (ablation) | Grid regularization dewarping · DocUNet benchmark | ED: 908.84 -> 896.48 | Improved |
| replace proposed grid regularization with TFI, using the same boundary points (ablation) | Grid regularization dewarping · DocUNet benchmark | CER: 0.3511 (0.183) -> 0.3379 (0.165) | Hurt |
| replace proposed grid regularization with TPS, using the same boundary points (ablation) | Grid regularization dewarping · DocUNet benchmark | ED: 1513.04 -> 1457.30 | 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.
- DocUNet — DocUNet: Document Image Unwarping via a Stacked U-Net (CVPR 2018) · better on 4 of 4 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
- Axis-Aligned Document Dewarping (AAAI 2026 · similarity 0.89)
- DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks (ICCV 2019 · similarity 0.86)
- D2Dewarp: Dual Dimensions Geometric Representation Learning Based Document Image Dewarping (CVPR 2026 · similarity 0.86)
- Fourier Document Restoration for Robust Document Dewarping and Recognition (CVPR 2022 · similarity 0.85)
- DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks (CVPR 2024 · similarity 0.81)
- DocNLC: A Document Image Enhancement Framework with Normalized and Latent Contrastive Representation for Multiple Degradations (AAAI 2024 · similarity 0.80)
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.
