Good news! Our new work exhibits state-of-the-art performances on DocUNet benchmark dataset: DocScanner
DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction
ACM MM 2021 Oral
Any questions or discussions are welcomed!
- For geometric unwarping, we train the GeoTr network using the Doc3d dataset.
- For illumination correction, we train the IllTr network based on the DRIC dataset.
- Download the pretrained models here and put them to
$ROOT/model_pretrained/
. - Geometric unwarping:
python inference.py
- Geometric unwarping and illumination rectification:
python inference.py --ill_rec True
- We use the same evaluation code as DocUNet benchmark dataset based on Matlab 2019a.
- Please compare the scores according to your Matlab version.
If you find this code useful for your research, please use the following BibTeX entry.
@inproceedings{feng2021doctr,
title={DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction},
author={Feng, Hao and Wang, Yuechen and Zhou, Wengang and Deng, Jiajun and Li, Houqiang},
booktitle={Proceedings of the 29th ACM International Conference on Multimedia},
pages={273--281},
year={2021}
}