Probabilistic moving least squares with spatial constraints for nonlinear color transfer between images

Youngbae Hwang, Joon Young Lee, In So Kweon, Seon Joo Kim

Research output: Contribution to journalArticle

Abstract

The color of a scene may vary from image to image because the photographs are taken at different times, with different cameras, and under different camera settings. To align the color of a scene between images, we introduce a novel color transfer framework based on a scattered point interpolation scheme. Compared to the conventional color transformation methods that use a parametric mapping or color distribution matching, we solve for a full nonlinear and nonparametric color mapping in the 3D RGB color space by employing the moving least squares framework. We further strengthen the transfer with a probabilistic modeling of the color transfer in the 3D color space as well as spatial constraints to deal with mis-alignments, noise, and spatially varying illumination. Experiments show the effectiveness of our method over previous color transfer methods both quantitatively and qualitatively. In addition, our framework can be applied for various instances of color transfer such as transferring color between different camera models, camera settings, and illumination conditions, as well as for video color transfers.

Original languageEnglish
Pages (from-to)1-12
Number of pages12
JournalComputer Vision and Image Understanding
Volume180
DOIs
Publication statusPublished - 2019 Mar 1

Fingerprint

Color
Cameras
Lighting
Interpolation

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

@article{9bf4b611df7a449592fdeb5d854314ee,
title = "Probabilistic moving least squares with spatial constraints for nonlinear color transfer between images",
abstract = "The color of a scene may vary from image to image because the photographs are taken at different times, with different cameras, and under different camera settings. To align the color of a scene between images, we introduce a novel color transfer framework based on a scattered point interpolation scheme. Compared to the conventional color transformation methods that use a parametric mapping or color distribution matching, we solve for a full nonlinear and nonparametric color mapping in the 3D RGB color space by employing the moving least squares framework. We further strengthen the transfer with a probabilistic modeling of the color transfer in the 3D color space as well as spatial constraints to deal with mis-alignments, noise, and spatially varying illumination. Experiments show the effectiveness of our method over previous color transfer methods both quantitatively and qualitatively. In addition, our framework can be applied for various instances of color transfer such as transferring color between different camera models, camera settings, and illumination conditions, as well as for video color transfers.",
author = "Youngbae Hwang and Lee, {Joon Young} and Kweon, {In So} and Kim, {Seon Joo}",
year = "2019",
month = "3",
day = "1",
doi = "10.1016/j.cviu.2018.11.001",
language = "English",
volume = "180",
pages = "1--12",
journal = "Computer Vision and Image Understanding",
issn = "1077-3142",
publisher = "Academic Press Inc.",

}

Probabilistic moving least squares with spatial constraints for nonlinear color transfer between images. / Hwang, Youngbae; Lee, Joon Young; Kweon, In So; Kim, Seon Joo.

In: Computer Vision and Image Understanding, Vol. 180, 01.03.2019, p. 1-12.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Probabilistic moving least squares with spatial constraints for nonlinear color transfer between images

AU - Hwang, Youngbae

AU - Lee, Joon Young

AU - Kweon, In So

AU - Kim, Seon Joo

PY - 2019/3/1

Y1 - 2019/3/1

N2 - The color of a scene may vary from image to image because the photographs are taken at different times, with different cameras, and under different camera settings. To align the color of a scene between images, we introduce a novel color transfer framework based on a scattered point interpolation scheme. Compared to the conventional color transformation methods that use a parametric mapping or color distribution matching, we solve for a full nonlinear and nonparametric color mapping in the 3D RGB color space by employing the moving least squares framework. We further strengthen the transfer with a probabilistic modeling of the color transfer in the 3D color space as well as spatial constraints to deal with mis-alignments, noise, and spatially varying illumination. Experiments show the effectiveness of our method over previous color transfer methods both quantitatively and qualitatively. In addition, our framework can be applied for various instances of color transfer such as transferring color between different camera models, camera settings, and illumination conditions, as well as for video color transfers.

AB - The color of a scene may vary from image to image because the photographs are taken at different times, with different cameras, and under different camera settings. To align the color of a scene between images, we introduce a novel color transfer framework based on a scattered point interpolation scheme. Compared to the conventional color transformation methods that use a parametric mapping or color distribution matching, we solve for a full nonlinear and nonparametric color mapping in the 3D RGB color space by employing the moving least squares framework. We further strengthen the transfer with a probabilistic modeling of the color transfer in the 3D color space as well as spatial constraints to deal with mis-alignments, noise, and spatially varying illumination. Experiments show the effectiveness of our method over previous color transfer methods both quantitatively and qualitatively. In addition, our framework can be applied for various instances of color transfer such as transferring color between different camera models, camera settings, and illumination conditions, as well as for video color transfers.

UR - http://www.scopus.com/inward/record.url?scp=85060762642&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060762642&partnerID=8YFLogxK

U2 - 10.1016/j.cviu.2018.11.001

DO - 10.1016/j.cviu.2018.11.001

M3 - Article

AN - SCOPUS:85060762642

VL - 180

SP - 1

EP - 12

JO - Computer Vision and Image Understanding

JF - Computer Vision and Image Understanding

SN - 1077-3142

ER -