GAN‐based tone curve learning for colour transfer

A new approach for reflecting the colour tone of a reference image on the input image is proposed. Depending on the source and reference image pairs, conventional statistical colour transfer methods often lead to undesirable colour transfer. Conversely, deep learning methods depend on prior learning...

Full description

Saved in:
Bibliographic Details
Published in:Electronics letters Vol. 58; no. 16; pp. 609 - 611
Main Authors: Ito, D., Sasaki, R., Uruma, K.
Format: Journal Article
Language:English
Published: Stevenage John Wiley & Sons, Inc 01.08.2022
Wiley
Subjects:
Color
Deep learning
Generative adversarial networks
Neural networks
Probability distribution
Statistical methods
ISSN:0013-5194, 1350-911X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A new approach for reflecting the colour tone of a reference image on the input image is proposed. Depending on the source and reference image pairs, conventional statistical colour transfer methods often lead to undesirable colour transfer. Conversely, deep learning methods depend on prior learning, which results in unnatural output images when inappropriate images are learned; moreover, in such situations, analysing what kind of colour transformation has actually been performed is difficult. This state of the art motivates the proposal of a new colour transfer method that estimates tone curves based on generative adversarial nets. This method does not require any data set other than input and reference images, thus enabling a more appropriate colour transfer. The superior output of the proposed method compared with some baseline approaches is demonstrated through experiments.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0013-5194
1350-911X
DOI:10.1049/ell2.12547