synthesis-in-style

KO | EN

gitlite — search

#javascript #python #hacktoberfest #react #ai #typescript #llm #go #golang #android #machine-learning #rust #deep-learning #linux

synthesis-in-style

★ 9 Open GitHub ↗

Code for our Paper "Synthesis in Style: Semantic Segmentation of Historical Documents using Synthetic Data"

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Synthesis in Style

![sis_example_high](https://user-images.githubusercontent.com/16731894/177955150-0e233fe0-4bd5-4ad9-88e4-2d1c2462755e.png)
This repository contains the code for the paper [Synthesis in Style: Semantic Segmentation of Historical Documents using Synthetic Data](https://arxiv.org/abs/2107.06777).
The trained models and benchmark dataset used for evaluation can be found [here](https://bartzi.de/research/synthesis_in_style).

## Installation

Make sure that Python (version >= 3.8) is installed.

In `stylegan_code_finder` directory execute: 
```
pip3 install -r requirements.txt -f https://download.pytorch.org/whl/torch_stable.html
```

For building the required cuda extensions `ninja` is required. (Installation under Ubuntu: `sudo apt-get install ninja-build`)

## Docker Image

You can also find a docker image with all necessary dependencies on [Docker Hub](https://hub.docker.com/repository/docker/hendraet/synthesis-in-style).

## Usage

For information how to use the code in this repository please refer to the [wiki](https://github.com/hendraet/synthesis-in-style/wiki/).

## License and Credits

The code used for the [EMANet](https://arxiv.org/abs/1907.13426) implementation is taken from [here](https://github.com/XiaLiPKU/EMANet).

The code for [TransUNet](https://arxiv.org/abs/2102.04306) was taken from [this](https://github.com/Beckschen/TransUNet) repository.

StyleGAN2 implementation and custom CUDA kernel codes are taken from official the official [NVIDIA repository](https://github.com/NVlabs/stylegan2), which is published under Nvidia Source Code License-NC.

## Citation

If you find the code useful, please cite our paper:

```bibtex
@INPROCEEDINGS{9956471,
  author={Bartz, Christian and Raetz, Hendrik and Otholt, Jona and Meinel, Christoph and Yang, Haojin},
  booktitle={2022 26th International Conference on Pattern Recognition (ICPR)}, 
  title={Synthesis in Style: Semantic Segmentation of Historical Documents using Synthetic Data}, 
  year={2022},
  volume={},
  number={},
  pages={3878-3884},
  doi={10.1109/ICPR56361.2022.9956471}
}
```

synthesis-in-style

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README