Awesome

This repo is the official implementation of the AAAI 2024 paper "DocNLC: A Document Image Enhancement Framework with Normalized and Latent Contrastive Representation for Multiple Degradations"

DocNLC: A Document Image Enhancement Framework with Normalized and Latent Contrastive Representation for Multiple Degradations

Requirements

torch == 1.7.1+cu101

numpy == 1.19.2

opencv-python == 4.5.1.48

Data Preparation

The structure of the training data is shown below:

├── Hybrid/

│ ├── Degraded/

│ │ ├── Blur/

│ │ ├── Noise/

│ │ ├── Shadow/

│ │ ├── Watermark/

│ │ ├── WithBack/

To generate the training dataset, run:

python generate_training_dataset.py (Coming soon)

Or download from: Pre-training Dataset (21.5G)

Train & Test

We control our hyper-parameters, such as batch size or learning rate, through exclusive yaml files. They are stored in the options folder. For pre-training, fine-tuning and testing, you should specify an appropriate yaml file. We have provided a sample file in the options folder.

Pre-train

Edit ./options/pretrain.yml
python pretrain.py

Fine-tune

Edit ./options/finetune.yml
python finetune.py

Test

Edit ./options/test.yml
python test.py

Note that the terminal output during the PSNR test is meaningless. In the next step we will evaluate the output images using the standard skimage.metrics.

Model Zoo

Pretrained Model	Pretrained Model
Asymmetric Comparison	One Drive
Symmetric Comparison	One Drive

Acknowledge

Our work is based on the following theoretical works:

and we are benefiting a lot from the following projects:

Citation

@inproceedings{wang2024docnlc,
  title={DocNLC: A Document Image Enhancement Framework with Normalized and Latent Contrastive Representation for Multiple Degradations},
  author={Wang, Ruilu and Xue, Yang and Jin, Lianwen},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={38},
  number={6},
  pages={5563--5571},
  year={2024}
}