Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2507.15000 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908652130009088 |
|---|---|
| author | Wang, Chaoyun Shen, I-Chao Igarashi, Takeo Jiang, Caigui |
| author_facet | Wang, Chaoyun Shen, I-Chao Igarashi, Takeo Jiang, Caigui |
| contents | Document dewarping is crucial for many applications. However, existing learning-based methods rely heavily on supervised regression with annotated data without fully leveraging the inherent geometric properties of physical documents. Our key insight is that a well-dewarped document is defined by its axis-aligned feature lines. This property aligns with the inherent axis-aligned nature of the discrete grid geometry in planar documents. Harnessing this property, we introduce three synergistic contributions: for the training phase, we propose an axis-aligned geometric constraint to enhance document dewarping; for the inference phase, we propose an axis alignment preprocessing strategy to reduce the dewarping difficulty; and for the evaluation phase, we introduce a new metric, Axis-Aligned Distortion (AAD), that not only incorporates geometric meaning and aligns with human visual perception but also demonstrates greater robustness. As a result, our method achieves state-of-the-art performance on multiple existing benchmarks, improving the AAD metric by 18.2% to 34.5%. The code is publicly available at https://github.com/chaoyunwang/AADD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_15000 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Axis-Aligned Document Dewarping Wang, Chaoyun Shen, I-Chao Igarashi, Takeo Jiang, Caigui Computer Vision and Pattern Recognition Document dewarping is crucial for many applications. However, existing learning-based methods rely heavily on supervised regression with annotated data without fully leveraging the inherent geometric properties of physical documents. Our key insight is that a well-dewarped document is defined by its axis-aligned feature lines. This property aligns with the inherent axis-aligned nature of the discrete grid geometry in planar documents. Harnessing this property, we introduce three synergistic contributions: for the training phase, we propose an axis-aligned geometric constraint to enhance document dewarping; for the inference phase, we propose an axis alignment preprocessing strategy to reduce the dewarping difficulty; and for the evaluation phase, we introduce a new metric, Axis-Aligned Distortion (AAD), that not only incorporates geometric meaning and aligns with human visual perception but also demonstrates greater robustness. As a result, our method achieves state-of-the-art performance on multiple existing benchmarks, improving the AAD metric by 18.2% to 34.5%. The code is publicly available at https://github.com/chaoyunwang/AADD. |
| title | Axis-Aligned Document Dewarping |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.15000 |