automatic color-grading

Last update: Jan 5, 2023

Overview

color-matcher

Description

color-matcher enables color transfer across images which comes in handy for automatic color-grading of photographs, paintings and film sequences as well as light-field and stopmotion corrections. The methods behind the mappings are based on the approach from Reinhard et al., an analytical solution to a Multi-Variate Gaussian Distribution (MVGD) transfer, the Monge-Kantorovich solution as proposed by Pitie et al. and classical histogram matching.

Results

	Source	Target	Result
Photograph
Film sequence
Light-field correction
Paintings

Installation

via pip:
1. install with pip3 install color-matcher
2. type color-matcher -h to the command line once installation finished
from source:
1. install Python from https://www.python.org/
2. download the source using git clone https://github.com/hahnec/color-matcher.git
3. go to the root directory cd color-matcher
4. load dependencies $ pip3 install -r requirements.txt
5. install with python3 setup.py install
6. if installation ran smoothly, enter color-matcher -h to the command line

CLI Usage

From the root directory of your downloaded repo, you can run the tool on the provided test data by

color-matcher -s './tests/data/scotland_house.png' -r './tests/data/scotland_plain.png'

on a UNIX system where the result is found at ./tests/data/. A windows equivalent of the above command is

color-matcher --src=".\\tests\\data\\scotland_house.png" --ref=".\\tests\\data\\scotland_plain.png"

Alternatively, you can specify the method or select your images manually with

color-matcher --win --method='hm-mkl-hm'

Note that batch processing is possible by passing a source directory, e.g., via

color-matcher -s './tests/data/' -r './tests/data/scotland_plain.png'

More information on optional arguments, can be found using the help parameter

color-matcher -h

API Usage

from color_matcher import ColorMatcher
from color_matcher.io_handler import load_img_file, save_img_file, FILE_EXTS
from color_matcher.normalizer import Normalizer
import os

img_ref = load_img_file('./tests/data/scotland_plain.png')

src_path = '.'
filenames = [os.path.join(src_path, f) for f in os.listdir(src_path)
                     if f.lower().endswith(FILE_EXTS)]

for i, fname in enumerate(filenames):
    img_src = load_img_file(fname)
    obj = ColorMatcher(src=img_src, ref=img_ref, method='mkl')
    img_res = obj.main()
    img_res = Normalizer(img_res).uint8_norm()
    save_img_file(img_res, os.path.join(os.path.dirname(fname), str(i)+'.png'))

Citation

@misc{hahne2020plenopticam,
      title={PlenoptiCam v1.0: A light-field imaging framework},
      author={Christopher Hahne and Amar Aggoun},
      year={2020},
      eprint={2010.11687},
      archivePrefix={arXiv},
      primaryClass={eess.IV}
}

Author

Christopher Hahne

You might also like...

H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.

H2O H2O is an in-memory platform for distributed, scalable machine learning. H2O uses familiar interfaces like R, Python, Scala, Java, JSON and the Fl

6.1k Jan 5, 2023

Comments

Color-matcher batch processing

I've just discovered color-matcher and find it potentially very useful for preprocessing histopathological datasets for deep learning. I can't, however, find a way to use it in batch mode - that is - is there any way to load more than one source image and/or more than one target image to process larger image datasets in batch?

opened by SahPet 4
Doc suggests pip3 for install, Anaconda seems to work with pip only

I'm using Anaconda (Conda 4.9.2) and used the documentation's suggested pip3 install procedure for color-matcher, but I couldn't run it from the command prompt. However, when I installed it via pip (just pip) it worked fine.

I ain't entirely sure if this fella got Python 3.8 and Python 2.7 both in there, but somehow I can only get it to run by entering only color-matcher in the command line after installing through pip as opposed to pip3.

Might need an extra line in the documentation saying do this if you're using Anaconda or Python 2.x or something, I ain't entirely sure of what's going on behind the scenes really.

opened by torridgristle 1
Rendering videos

hi thanks for this great piece of code.

I am doing some tests on videos, is there a specific mode to ensure temporal consistency for video rendering?

I have tried a few image by image processing, and the results are subject to flickering, especially when there are strong intense areas, even small (the blinking crosswalk light in the below examples)

thanks

https://user-images.githubusercontent.com/29961693/178616708-e5b7fd6d-b2aa-4dd1-abe8-2908267621b5.mp4

https://user-images.githubusercontent.com/29961693/178616722-381ff433-ebaa-423d-801b-a518816068c3.mp4

opened by Tetsujinfr 1
[ Feature Request ] CLUT Output

The ability to save a CLUT of the color transformation would be useful for applying the transformation to other scenes / videos / games, and for tweaking the transformation with other tools for artistic purposes with color-matcher's output as the starting point.

Look I got the early morning lightheadedness and I wanna gush about this program, this has saved me such a hassle trying to white balance the most fucked up of photos with purple skin, absolutely marvelous. Software intended for auto white-balance just made em all green, but this matched it to a collage of similar faces in better lighting and damn if it isn't just the best outcome I could imagine for the material. I could overhaul an entire dataset and augment the shit out of it if I wanted. This is baller.
feature-request

opened by torridgristle 6

Releases(v0.5.0)

v0.5.0(Aug 25, 2021)
This release contains the following changes:

fixes to handle gray-scale and alpha-channel images

refactored code for mkl_solver() method for better readability (comply with PEP8)

added API function ColorMatcher.transfer(src=src, ref=ref, method='hm-mkl-hm')

note that the existing ColorMatcher(src=src, ref=ref, method='hm-mkl-hm').main() is still viable

Source code(tar.gz)
Source code(zip)
color-matcher-0.5.0.tar.gz(894.71 KB)
color_matcher-0.5.0-py3-none-any.whl(1.72 MB)
v0.4.0(Feb 21, 2021)
Release v0.4.0 contains the following changes:

new interface method 'mvgd' for analytical solution of a Multi-Variate Gaussian Distribution (MVGD) transfer

move of the CI pipeline to GitHub Actions

Source code(tar.gz)
Source code(zip)
color-matcher-0.4.0.tar.gz(882.03 KB)
color_matcher-0.4.0-py3-none-any.whl(1.71 MB)
v0.3.4(Dec 22, 2020)
This minor release update covers the following changes:

output directory creation for processing a stack of input images

CLI feedback about location of result(s)

minor update on the documentation

expand CLI unit tests (e.g. image dimensions)

Source code(tar.gz)
Source code(zip)
color-matcher-0.3.4.tar.gz(881.78 KB)
color_matcher-0.3.4-py3-none-any.whl(1.71 MB)
v0.3.2(Dec 21, 2020)
Release v0.3.2 contains the following changes:

resolves image file batch processing from the command line following issue #1

reduces repo size by removing redundant image

set default paths for command line usage

Source code(tar.gz)
Source code(zip)
color-matcher-0.3.2.tar.gz(880.98 KB)
color_matcher-0.3.2-py3-none-any.whl(1.71 MB)
v0.3.1(Dec 6, 2020)
The release v0.3.1 includes some minor updates and bug fixes including:

added support for Jupyter Demo using Binder

resolve uppercase letters provided in method string

renaming of ./test to ./tests folder

fix for TestPyPi upload in TravisCI

removed .DS_Stores files

Source code(tar.gz)
Source code(zip)
color-matcher-0.3.1.tar.gz(880.95 KB)
color_matcher-0.3.1-py3-none-any.whl(1.71 MB)
v0.3.0(Aug 31, 2020)

Release v0.3.0 features an analytical solution to the color transfer based on Multi-Variate-Gaussian Distribution (MVGD).
Source code(tar.gz)
Source code(zip)
color-matcher-0.3.0.tar.gz(878.83 KB)
color_matcher-0.3.0-py3-none-any.whl(1.71 MB)
v0.2.6(Aug 30, 2020)

This release fixes an issue when passing a directory as source in CLI usage (e.g. -s './' or --src='./')
Source code(tar.gz)
Source code(zip)
color-matcher-0.2.6.tar.gz(878.64 KB)
color_matcher-0.2.6-py3-none-any.whl(1.71 MB)
v0.2.5(May 25, 2020)
add code coverage

Source code(tar.gz)
Source code(zip)
color-matcher-0.2.5.tar.gz(878.62 KB)
color_matcher-0.2.5-py3-none-any.whl(1.71 MB)
v0.2.2(Apr 18, 2020)
fix in CLI usage: strip quotes and whitespaces

Source code(tar.gz)
Source code(zip)
color-matcher-0.2.2.tar.gz(878.40 KB)
color_matcher-0.2.2-py3-none-any.whl(1.71 MB)
v0.2.0(Apr 16, 2020)
improved Reinhard method

Source code(tar.gz)
Source code(zip)
color-matcher-0.2.0.tar.gz(878.34 KB)
color_matcher-0.2.0-py3-none-any.whl(1.71 MB)
v0.1.6(Apr 4, 2020)
improve unit tests

Source code(tar.gz)
Source code(zip)
color-matcher-0.1.6.tar.gz(878.61 KB)
color_matcher-0.1.6-py3-none-any.whl(1.71 MB)
v0.1.5(Apr 3, 2020)
add method from Reinhard

add travis CI

Source code(tar.gz)
Source code(zip)
color-matcher-0.1.5.tar.gz(878.56 KB)
color_matcher-0.1.5-py3-none-any.whl(1.71 MB)

automatic color-grading

Related tags

Overview

color-matcher

Description

Results

Installation

CLI Usage

API Usage

Citation

Author

You might also like...

Spatial color quantization in Rust

Rendering color and depth images for ShapeNet models.

3DMV jointly combines RGB color and geometric information to perform 3D semantic segmentation of RGB-D scans.

A very simple baseline to estimate 2D & 3D SMPL-compatible keypoints from a single color image.

Implementation of GGB color space

A minimal solution to hand motion capture from a single color camera at over 100fps. Easy to use, plug to run.

An end-to-end image translation model with weight-map for color constancy

Blender Add-on that sets a Material's Base Color to one of Pantone's Colors of the Year

Comments

Color-matcher batch processing

Doc suggests pip3 for install, Anaconda seems to work with pip only

Rendering videos

[ Feature Request ] CLUT Output

Releases(v0.5.0)

v0.5.0(Aug 25, 2021)

v0.4.0(Feb 21, 2021)

v0.3.4(Dec 22, 2020)

v0.3.2(Dec 21, 2020)

v0.3.1(Dec 6, 2020)

v0.3.0(Aug 31, 2020)

v0.2.6(Aug 30, 2020)

v0.2.5(May 25, 2020)

v0.2.2(Apr 18, 2020)

v0.2.0(Apr 16, 2020)

v0.1.6(Apr 4, 2020)

v0.1.5(Apr 3, 2020)

Owner

hahnec

SpineAI Bilsky Grading With Python

Automatic self-diagnosis program (python required)Automatic self-diagnosis program (python required)

git《Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser》(2021) GitHub: [fig5]

Lipstick ain't enough: Beyond Color-Matching for In-the-Wild Makeup Transfer (CVPR 2021)

An official TensorFlow implementation of “CLCC: Contrastive Learning for Color Constancy” accepted at CVPR 2021.

Software & Hardware to do multi color printing with Sharpies

Reference code for the paper CAMS: Color-Aware Multi-Style Transfer.

Fast Soft Color Segmentation