/Color_Transfer_Histogram_Analogy

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

Primary LanguagePythonGNU Affero General Public License v3.0AGPL-3.0

Deep Color Transfer using Histogram Analogy

License CC BY-NC

Teaser image 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.

This repository contains the official PyTorch implementation of the following paper:

Deep Color Transfer using Histogram Analogy
Junyong Lee, Hyeongseok Son, Gunhee Lee, Jonghyeop Lee, Sunghyun Cho and Seungyong Lee, CGI 2020

Getting Started

Prerequisites

Tested environment

Ubuntu Python PyTorch CUDA

  1. Install requirements

    • pip install -r requirements.txt
  2. Pre-trained models

    • Download and unzip pretrained weights under [CHECKPOINT_ROOT]:

      ├── [CHECKPOINT_ROOT]
      │   ├── *.pth
      

      NOTE:

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

Testing the network

  1. Place input images and their segment maps should be placed under ./test/input and ./test/seg_in, respectively. Place target images and their segment maps under ./test/target and ./test/seg_tar, respectively.

  2. Test the network:

python test.py --dataroot [test folder path] --checkpoints_dir [CHECKPOINT_ROOT]
# e.g., python test.py --dataroot test --checkpoints_dir checkpoints
* 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
```

Citation

If you find this code useful, please consider citing:

@article{Lee_2020_CTHA,
  author = {Lee, Junyong and Son, Hyeongseok and Lee, Gunhee and Lee, Jonghyeop and Cho, Sunghyun and Lee, Seungyong},
  title = {Deep Color Transfer using Histogram Analogy},
  journal = {The Visual Computer},
  volume = {36},
  number = {10},
  pages = {2129--2143},
  year = 2020,
}

Contact

Open an issue for any inquiries. You may also have contact with junyonglee@postech.ac.kr

Resources

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

Link
Paper PDF
Supplementary Files
Checkpoint Files

License

This software is being made available under the terms in the LICENSE file.

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

About Coupe Project

Project ‘COUPE’ aims to develop software that evaluates and improves the quality of images and videos based on big visual data. To achieve the goal, we extract sharpness, color, composition features from images and develop technologies for restoring and improving by using them. In addition, personalization technology through user reference analysis is under study.

Please checkout other Coupe repositories in our Posgraph github organization.

Useful Links