Research map / Image generation / Image restoration
DocUNet: Document Image Unwarping via a Stacked U-Net
Ke Ma, Zhixin Shu, Xue Bai, Jue Wang, Dimitris Samaras
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 |
|---|---|---|---|
| use end-to-end DocUNet instead of Tian et al. [27] | document image unwarping · DocUNet benchmark | MS-SSIM: 0.13 -> 0.41 | Improved |
| use end-to-end DocUNet instead of Tian et al. [27] | document image unwarping · DocUNet benchmark | LD: 33.69 -> 14.08 | Improved |
| use end-to-end DocUNet instead of Tian et al. [27] | document image unwarping · DocUNet benchmark | time(s): 212 -> 4 | Improved |
| replace Lf and Lb with conventional L1 loss (ablation) | stacked U-Net · DocUNet benchmark | MS-SSIM: 0.41 -> 0.40 | Hurt |
| replace Lf and Lb with conventional L1 loss (ablation) | stacked U-Net · DocUNet benchmark | LD: 14.08 -> 14.85 | Hurt |
| use a single U-Net instead of a stacked U-Net (ablation) | document unwarping with L1 loss · DocUNet benchmark | MS-SSIM: 0.40 -> 0.35 | Hurt |
| use a single U-Net instead of a stacked U-Net (ablation) | document unwarping with L1 loss · DocUNet benchmark | LD: 14.85 -> 15.73 | Hurt |
Later papers that compared with this method
2 later accepted papers report DocUNet as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Revisiting Document Image Dewarping by Grid Regularization (CVPR 2022 · better on 4 of 4 shared results)
- End-to-End Piece-Wise Unwarping of Document Images (ICCV 2021 · 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
- DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks (ICCV 2019 · similarity 0.88)
- End-to-End Piece-Wise Unwarping of Document Images (ICCV 2021 · similarity 0.88)
- Geometric Representation Learning for Document Image Rectification (ECCV 2022 · similarity 0.86)
- Foreground and Text-lines Aware Document Image Rectification (ICCV 2023 · similarity 0.86)
- DocFormerv2: Local Features for Document Understanding (AAAI 2024 · similarity 0.82)
- Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark (CVPR 2025 · 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.
