Entropic Regularisation of Robust Optimal Transport

Rozenn Dahyot; Hana Alghamdi; Mairead Grogan

doi:10.21427/w611-mb37

Entropic Regularisation of Robust Optimal Transport

Rozenn Dahyot, Hana Alghamdi, Mairead Grogan

Research output: Contribution to conference › Paper › peer-review

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.

Original language	English
DOIs	https://doi.org/10.21427/w611-mb37
Publication status	Published - 1 Jan 2019
Externally published	Yes
Event	IMVIP 2019: Irish Machine Vision & Image Processing - Technological University Dublin, Dublin, Ireland Duration: 28 Aug 2019 → 30 Aug 2019

Conference

Conference	IMVIP 2019: Irish Machine Vision & Image Processing
Country/Territory	Ireland
City	Dublin
Period	28/08/19 → 30/08/19

Keywords

colour transfer
Euclidean distance
probability density functions
colour distributions
Optimal Transport
entropy regularisation

Access to Document

10.21427/w611-mb37Licence: CC BY-NC-SA

Cite this

@conference{253edac772824c73802338aaabd48dbf,

title = "Entropic Regularisation of Robust Optimal Transport",

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{\textquoteright}s formulation can also be understood as a new robust Optimal Transport based framework with entropy regularisation over marginals.",

keywords = "colour transfer, Euclidean distance, probability density functions, colour distributions, Optimal Transport, entropy regularisation",

author = "Rozenn Dahyot and Hana Alghamdi and Mairead Grogan",

year = "2019",

month = jan,

day = "1",

doi = "10.21427/w611-mb37",

language = "English",

note = "IMVIP 2019: Irish Machine Vision \& Image Processing ; Conference date: 28-08-2019 Through 30-08-2019",

}

TY - CONF

T1 - Entropic Regularisation of Robust Optimal Transport

AU - Dahyot, Rozenn

AU - Alghamdi, Hana

AU - Grogan, Mairead

PY - 2019/1/1

Y1 - 2019/1/1

N2 - 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.

AB - 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.

KW - colour transfer

KW - Euclidean distance

KW - probability density functions

KW - colour distributions

KW - Optimal Transport

KW - entropy regularisation

U2 - 10.21427/w611-mb37

DO - 10.21427/w611-mb37

M3 - Paper

T2 - IMVIP 2019: Irish Machine Vision & Image Processing

Y2 - 28 August 2019 through 30 August 2019

ER -

Entropic Regularisation of Robust Optimal Transport

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this