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 …

Simfir: A simple framework for fisheye image rectification with self-supervised representation learning

H Feng, W Wang, J Deng, W Zhou… - Proceedings of the …, 2023 - openaccess.thecvf.com
In fisheye images, rich distinct distortion patterns are regularly distributed in the image
plane. These distortion patterns are independent of the visual content and provide …

Visual Text Meets Low-level Vision: A Comprehensive Survey on Visual Text Processing

Y Shu, W Zeng, Z Li, F Zhao, Y Zhou - ar**
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 …

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 …

Am I readable? Transfer learning based document image rectification

P Kumari, S Das - International Journal on Document Analysis and …, 2024 - Springer
Document image rectification is a commonly explored problem in computer vision. However,
in recent works, the improvements made on a distorted document page are mostly confined …

Do-GOOD: towards distribution shift evaluation for pre-trained visual document understanding models

J He, Y Hu, L Wang, X Xu, N Liu, H Liu… - Proceedings of the 46th …, 2023 - dl.acm.org
Numerous pre-training techniques for visual document understanding (VDU) have recently
shown substantial improvements in performance across a wide range of document tasks …