M6doc: A large-scale multi-format, multi-type, multi-layout, multi-language, multi-annotation category dataset for modern document layout analysis

H Cheng, P Zhang, S Wu, J Zhang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Document layout analysis is a crucial prerequisite for document understanding, including
document retrieval and conversion. Most public datasets currently contain only PDF …

Foreground and text-lines aware document image rectification

H Li, X Wu, Q Chen, Q Xiang - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
This paper aims at the distorted document image rectification problem, the objective to
eliminate the geometric distortion in the document images and realize document …

Deep unrestricted document image rectification

H Feng, S Liu, J Deng, W Zhou… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
In recent years, tremendous efforts have been made on document image rectification, but
existing advanced algorithms are limited to processing restricted document images, ie, the …

Layout-aware single-image document flattening

P Li, W Quan, J Guo, DM Yan - ACM Transactions on Graphics, 2023 - dl.acm.org
Single image rectification of document deformation is a challenging task. Although some
recent deep learning-based methods have attempted to solve this problem, they cannot …

DocScanner: Robust document image rectification with progressive learning

H Feng, W Zhou, J Deng, Q Tian, H Li - arXiv preprint arXiv:2110.14968, 2021 - arxiv.org
Compared with flatbed scanners, portable smartphones provide more convenience for
physical document digitization. However, such digitized documents are often distorted due …

DocRes: A Generalist Model Toward Unifying Document Image Restoration Tasks

J Zhang, D Peng, C Liu, P Zhang… - Proceedings of the …, 2024 - openaccess.thecvf.com
Document image restoration is a crucial aspect of Document AI systems as the quality of
document images significantly influences the overall performance. Prevailing methods …

Template-guided illumination correction for document images with imperfect geometric reconstruction

F Hertlein, A Naumann - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
To facilitate the transition into the digital era, it is necessary to digitize printed documents
such as forms and invoices. Due to the presence of diverse lighting conditions and …

Matadoc: margin and text aware document dewarping for arbitrary boundary

B Dai, Q Xie, Y Li, X Qin, C Zhang, K Yao… - arXiv preprint arXiv …, 2023 - arxiv.org
Document dewarping from a distorted camera-captured image is of great value for OCR and
document understanding. The document boundary plays an important role which is more …

Appearance enhancement for camera-captured document images in the wild

J Zhang, L Liang, K Ding, F Guo… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Camera-captured document images usually suffer from various appearance degradations,
which hamper the clarity of content and preclude subsequent analysis and recognition …

Inv3D: a high-resolution 3D invoice dataset for template-guided single-image document unwarping

F Hertlein, A Naumann, P Philipp - International Journal on Document …, 2023 - Springer
Numerous business workflows involve printed forms, such as invoices or receipts, which are
often manually digitalized to persistently search or store the data. As hardware scanners are …