Interactive transfer of human facial color

Authors:
Kyoung Chin Seo;Giroo Shin;Sang Wook Lee
Affiliations:
Dept. of Media Technology, Sogang University, Seoul, Korea;GOMID Co.Ltd., Seoul, Korea;Dept. of Media Technology, Sogang University, Seoul, Korea
Venue:
PCM'05 Proceedings of the 6th Pacific-Rim conference on Advances in Multimedia Information Processing - Volume Part II
Year:
2005

Citing 14
Cited 0

A physical approach to color image understanding

International Journal of Computer Vision
Reflection from layered surfaces due to subsurface scattering

SIGGRAPH '93 Proceedings of the 20th annual conference on Computer graphics and interactive techniques
Acquiring the reflectance field of a human face

Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Image analogies

Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Image quilting for texture synthesis and transfer

Proceedings of the 28th annual conference on Computer graphics and interactive techniques
A practical model for subsurface light transport

Proceedings of the 28th annual conference on Computer graphics and interactive techniques
A practical model for subsurface light transport

Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Transferring color to greyscale images

Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Color Transfer between Images

IEEE Computer Graphics and Applications
Texture Synthesis by Non-Parametric Sampling

ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Image-based skin color and texture analysis/synthesis by extracting hemoglobin and melanin information in the skin

ACM SIGGRAPH 2003 Papers
Poisson matting

ACM SIGGRAPH 2004 Papers
Colorization using optimization

ACM SIGGRAPH 2004 Papers
Image-based BRDF measurement including human skin

EGWR'99 Proceedings of the 10th Eurographics conference on Rendering

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper focuses on a new and intuitive method for transferring and modifying human skin color based on statistical and photometric clues between two photographs. We construct skin color transfer model for both photographs by clustering pixels along the direction of principal vector as a result of least square fitting. Color and texture features of source skin is transferred to that of target skin by changing Gaussian distribution of each pair of the matched clusters. Discarding or selecting the clusters including specular component also enables to generate various tones of skin color. Interactive tuning of each color cluster adds various effects like weakening the color of flush and exaggerating the traits of face with make-up. We demonstrate realistic skin color transfer results improved from previous works and intuitive handling of skin colors by the skin color transfer model.