Awesome
<p align="center"> <img src="figs/architecture.png"> </p>GCDRNet
This repository contains the inference code for our paper Appearance Enhancement for Camera-captured Document Images in the Wild, which has been accepted for IEEE Transactions on Artificial Intelligence.
Inference (model weights can be downloaded here)
Place the distorted image in the folder ./distorted, run the following command, and the results will be saved in the folder ./enhanced.
python infer.py
RealDAE
RealDAE (Real-world Document Image Appearance Enhancement) is a real-world dataset designed explicitly for camera-captured document images in the wild. It containes 600 pairs of degraded camera-captured document images and corresponding manually enhanced ground-truths (aligned at the pixel level). It can be downloaded here. Some examples are illustrated as below.
<p align="center"> <img src="figs/example.png"> </p>Citation
If you are using our code and data, please cite our paper.
@article{zhang2023appearance,
title={Appearance Enhancement for Camera-captured Document Images in the Wild},
author={Zhang, Jiaxin and Liang, Lingyu and Ding, Kai and Guo, Fengjun and Jin, Lianwen},
journal={IEEE Transactions on Artificial Intelligence},
year={2023}}