%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
This folder contains the Matlab and C++ code for the colour transfer algorithm detailed in 'L2 Divergence for robust colour transfer'.
You can download this source code for free, use and change it as
you like, but please cite our paper:
L2 Divergence for robust colour transfer
Mairead Grogan and Rozenn Dahyot
Computer Vision and Image Understanding 2019
A bibtex entry for this paper is given below:
@article{GROGAN2019,
title = "L2 Divergence for robust colour transfer",
journal = "Computer Vision and Image Understanding",
year = "2019",
issn = "1077-3142",
doi = "https://doi.org/10.1016/j.cviu.2019.02.002",
url = "http://www.sciencedirect.com/science/article/pii/S1077314219300177",
author = "Mairead Grogan and Rozenn Dahyot",
keywords = "Colour Transfer, L2 Registration, Re-colouring, Colour Grading",
abstract = "Optimal Transport (OT) is a very popular framework for performing
colour transfer in images and videos. We have proposed an alternative framework
where the cost function used for inferring a parametric transfer function is
defined as the robust L2 divergence between two probability density functions Grogan
and Dahyot (2015). In this paper, we show that our approach combines many advantages of state of the
art techniques and outperforms many recent algorithms as measured quantitatively with standard quality metrics,
and qualitatively using perceptual studies Grogan and Dahyot (2017). Mathematically, our formulation is presented
in contrast to the OT cost function that shares similarities with our cost function. Our formulation, however, is
more flexible as it allows colour correspondences that may be available to be taken into account and performs well
despite potential occurrences of correspondence outlier pairs. Our algorithm is shown to be fast, robust and it easily
allows for user interaction providing freedom for artists to fine tune the recoloured images and videos Grogan et al. (2017)."
}
Contact: Mairead Grogan [email protected]
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%