Entropic Regularisation of Robust Optimal Transport
Computer Vision and Pattern Recognition
2019-07-15 v1 Machine Learning
Machine Learning
Abstract
Grogan et al [11,12] have recently proposed a solution to colour transfer by minimising the Euclidean distance L2 between two probability density functions capturing the colour distributions of two images (palette and target). It was shown to be very competitive to alternative solutions based on Optimal Transport for colour transfer. We show that in fact Grogan et al's formulation can also be understood as a new robust Optimal Transport based framework with entropy regularisation over marginals.
Keywords
Cite
@article{arxiv.1905.12678,
title = {Entropic Regularisation of Robust Optimal Transport},
author = {Rozenn Dahyot and Hana Alghamdi and Mairead Grogan},
journal= {arXiv preprint arXiv:1905.12678},
year = {2019}
}
Comments
8 pages