Three methods of color transfer implemented in python.
Project description
Color Transfer in Python
Three methods of color transfer implemented in python.
Examples
input img | reference img | mean std transfer | lab mean std transfer | pdf transfer + regrain
Pip Wheels
install
pip install python-color-transfer
usage
from python_color_transfer.color_transfer import ColorTransfer
PT = ColorTransfer()
# input image and reference image
img_arr_in = cv2.imread(img_path)
img_arr_ref = cv2.imread(ref_path)
# pdf transfer
img_arr_reg = PT.pdf_transfer(img_arr_in=img_arr_in,
img_arr_ref=img_arr_ref,
regrain=True)
# mean transfer
img_arr_mt = PT.mean_std_transfer(img_arr_in=img_arr_in,
img_arr_ref=img_arr_ref)
# lab transfer
img_arr_lt = PT.lab_transfer(img_arr_in=img_arr_in,
img_arr_ref=img_arr_ref)
From source
Clone
git clone https://github.com/pengbo-learn/python-color-transfer.git
Environment
- python3
- install dependency by
sh env.sh
.
# env.sh
pip3 install opencv-python==4.2.0.34
pip3 install numpy==1.19.3
Run
# python demo.py
/root/python_color_transfer/imgs/scotland_house.png: 361x481x3
/root/python_color_transfer/imgs/scotland_plain.png: 361x481x3
pdf transfer time: 0.67s
regrain time: 0.49s
mean std transfer time: 0.04s
lab mean std transfer time: 0.22s
save to /root/python_color_transfer/imgs/scotland_display.png
/root/python_color_transfer/imgs/house.jpeg: 512x768x3
/root/python_color_transfer/imgs/hats.png: 512x768x3
pdf transfer time: 1.47s
regrain time: 1.16s
mean std transfer time: 0.09s
lab mean std transfer time: 0.09s
save to /root/python_color_transfer/imgs/house_display.png
/root/python_color_transfer/imgs/fallingwater.png: 727x483x3
/root/python_color_transfer/imgs/autumn.jpg: 727x1000x3
pdf transfer time: 1.87s
regrain time: 0.87s
mean std transfer time: 0.12s
lab mean std transfer time: 0.11s
save to /root/python_color_transfer/imgs/fallingwater_display.png
/root/python_color_transfer/imgs/tower.jpeg: 743x1280x3
/root/python_color_transfer/imgs/sunset.jpg: 743x1114x3
pdf transfer time: 2.95s
regrain time: 2.83s
mean std transfer time: 0.23s
lab mean std transfer time: 0.21s
save to /root/python_color_transfer/imgs/tower_display.png
Methods
Let input image be I, reference image be R and output image be O.
Let f{I}(r, g, b), f{R}(r, g, b) be probability density functions of I and R's rgb values.
-
mean std transfer
O = (I - mean(I)) / std(I) * std(R) + mean(R).
-
lab mean transfer
I' = rgb2lab(I),
R' = rgb2lab(R),
O' = (I' - mean(I')) / std(I') * std(R') + mean(R'),
O = lab2rgb(O'). -
pdf transfer
O = t(I), where t: R^3-> R^3 is a continous mapping so that f{t(I)}(r, g, b) = f{R}(r, g, b).
References
-
pdf transfer
Automated colour grading using colour distribution transfer by F. Pitie , A. Kokaram and R. Dahyot.
Author's matlab implementation -
lab mean transfer
Color Transfer between Images by Erik Reinhard, Michael Ashikhmin, Bruce Gooch and Peter Shirley.
Open source's python implementation
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for python_color_transfer-0.1.1b0.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | fced1d54d09181450a83d0ddcc6179b999874a269d4cb7a66e9cc22a7c08daa7 |
|
MD5 | ed21842b6bd0981a4705a4490f68b8b8 |
|
BLAKE2b-256 | 4af87a8b291660dcf4f02ad7437d3757aa156e45b6b89785c94851176522c849 |
Hashes for python_color_transfer-0.1.1b0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 69021f873efe9dbc6abaf825061a6a3ceda951efbc18bd8af728a2d415bab122 |
|
MD5 | 13be477c99be4b9e451ea31a8d439718 |
|
BLAKE2b-256 | 37ea246027b6b612ee1a7bbc642006bbdf4c0aec3a0f2a9548be89907c564747 |