Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/codeslake/Color_Transfer_Histogram_Analogy

[CGI 2020] Official PyTorch Implementation for "Deep Color Transfer using Histogram Analogy"
https://github.com/codeslake/Color_Transfer_Histogram_Analogy

color-transfer deep-learning histogram-analogy pytorch

Last synced: about 2 months ago
JSON representation

[CGI 2020] Official PyTorch Implementation for "Deep Color Transfer using Histogram Analogy"

Host: GitHub
URL: https://github.com/codeslake/Color_Transfer_Histogram_Analogy
Owner: codeslake
License: agpl-3.0
Created: 2020-08-19T00:33:03.000Z (about 4 years ago)
Default Branch: master
Last Pushed: 2024-04-02T21:46:22.000Z (6 months ago)
Last Synced: 2024-04-20T17:00:48.929Z (5 months ago)
Topics: color-transfer, deep-learning, histogram-analogy, pytorch
Language: Python
Homepage:
Size: 13.6 MB
Stars: 152
Watchers: 5
Forks: 32
Open Issues: 1
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

README

        ## Deep Color Transfer using Histogram Analogy
_{Official PyTorch Implementation of the CGI 2020 Paper}
_{[Project](https://junyonglee.me/projects/CTHA) | [Paper](https://link.springer.com/epdf/10.1007/s00371-020-01921-6?sharing_token=m2UzXwVlSCP8CbRYNrEcnve4RwlQNchNByi7wbcMAY5_mQV2iPdNT8_ORizvbX3p8mina4UHEjoKsvegf0S_FwC3Yo3cBRV6mlx1mdbvv3CiiREpz3ZqyJuRGmHbygkNL_7X-3hd2CMGSxgPtF22LPsyjpEfhG1R_bNHSSVNvbc%3D) | [Supp](https://www.dropbox.com/s/jxvg6ize41g43vj/Additional_Result.pdf?raw=1) | [Slide](https://www.dropbox.com/s/jbnp7omqre2pu9b/2020_junyonglee.pdf?raw=1)}

This repo contains the evaluation code for the following paper:

> [**Deep Color Transfer using Histogram Analogy**](https://junyonglee.me/projects/CTHA)


> [Junyong Lee](https://junyonglee.me)¹, [Hyeongseok Son](https://sites.google.com/site/sonhspostech/)¹, Gunhee Lee², Jonghyeop Lee¹, [Sunghyun Cho](https://www.scho.pe.kr/)¹, and [Seungyong Lee](http://cg.postech.ac.kr/leesy/)¹


> ¹POSTECH, ²NCSOFT


> *The Visual Computer (special issue on CGI 2020) 2020*


> 



  

    

  





  



**Figure:** *Color transfer results on various source and reference image pairs. For visualization, the reference image is cropped to make a same size with other images.*

## Getting Started

### Prerequisites

*Tested environment*

![Ubuntu](https://img.shields.io/badge/Ubuntu-18.0.4-blue.svg?style=plastic)

![Python](https://img.shields.io/badge/Python-3.8.8-green.svg?style=plastic)

![PyTorch](https://img.shields.io/badge/PyTorch-1.8.0-green.svg?style=plastic)

![CUDA](https://img.shields.io/badge/CUDA-10.2-green.svg?style=plastic)

1. **Install requirements**

    * `pip install -r requirements.txt`

    * 

2. **Pre-trained models**

    * Download and unzip pretrained weights ([OneDrive](https://onedrive.live.com/download?resid=94530B7E5F49D254%21484&authkey=!AIw6wh6Vjo-IFWs) | [Dropbox](https://www.dropbox.com/s/lkwo9xg168e650i/checkpoints.zip?dl=1)) under `[CHECKPOINT_ROOT]`:

        ```

        ├── [CHECKPOINT_ROOT]

        │   ├── *.pth

        ```

        > **NOTE:**

        > 

        > `[CHECKPOINT_ROOT]` can be specified with the option `--checkpoints_dir`.

## Testing the network

* To test the network:

  ```bash

  python test.py --dataroot [test folder path] --checkpoints_dir [CHECKPOINT_ROOT]

  # e.g., python test.py --dataroot test --checkpoints_dir checkpoints

  ```

  > **Note:**

  >

  > * Input images and their segment maps should be placed under `./test/input` and `./test/seg_in`, respectively.

  > * Target images and their segment maps should be placed under `./test/target` and `./test/seg_tar`, respectively. 

  > * The test results will be saved under `./results/`.

* To turn on *semantic replacement*, add `--is_SR`:

  ```bash

  python test.py --dataroot [test folder path] --checkpoints_dir [ckpt path] --is_SR

  ```

## Contact

Open an issue for any inquiries.

You may also have contact with [[email protected]](mailto:[email protected])

## Resources

All material related to our paper is available via the following links:

## License

![License CC BY-NC](https://img.shields.io/badge/license-GNU_AGPv3-green.svg?style=plastic)


This software is being made available under the terms in the [LICENSE](LICENSE) file.

Any exemptions to these terms require a license from the Pohang University of Science and Technology.

## Citation

If you find this code useful, please consider citing:

```

@Article{Lee2020CTHA,

    author  = {Junyong Lee and Hyeongseok Son and Gunhee Lee and Jonghyeop Lee and Sunghyun Cho and Seungyong Lee},

    title   = {Deep Color Transfer using Histogram Analogy},

    journal = {The Visual Computer},

    volume  = {36},

    number  = {10},

    pages   = {2129--2143},

    year    = {2020},

}

```