[CGI 2020] Official PyTorch Implementation for "Deep Color Transfer using Histogram Analogy"
This repo contains the evaluation code for the following paper:
Deep Color Transfer using Histogram Analogy
Junyong Lee1, Hyeongseok Son1, Gunhee Lee2, Jonghyeop Lee1, Sunghyun Cho1, and Seungyong Lee1
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.
Tested environment
pip install -r requirements.txt
To test the network:
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
:
python test.py --dataroot [test folder path] --checkpoints_dir [ckpt path] --is_SR
Open an issue for any inquiries. You may also have contact with [email protected]
All material related to our paper is available via the following links:
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.
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},
}