Garment personalization via identity transfer

Roy Shilkrot; Daniel Cohen-Or; Ariel Shamir; Ligang Liu

doi:https://doi.org/10.1109/MCG.2012.90

Garment personalization via identity transfer

Roy Shilkrot, Daniel Cohen-Or, Ariel Shamir, Ligang Liu

School of Computer Science

Tel Aviv University

Research output: Contribution to journal › Article › peer-review

Abstract

A new system provides a virtual experience akin to trying on clothing. It clones the user's photographic image into a catalog of images of models wearing the desired garments. Simple offline training extracts the user's head. Segmentation accurately separates the face, hair, and background, employing both a three-kernel statistical model and graph cuts. The system adjusts the resulting image's skin color according to a statistical model and relights the head via spherical harmonics. Finally, using a parametric model, the system warps the clone's body dimensions to fit the user's dimensions. This creates high-quality compositions of the user's image and the given garment.

Original language	English
Article number	6253188
Pages (from-to)	62-72
Number of pages	11
Journal	IEEE Computer Graphics and Applications
Volume	33
Issue number	4
DOIs	https://doi.org/10.1109/MCG.2012.90
State	Published - 2013

Keywords

computer graphics
image enhancement
online cloning
photo processing

All Science Journal Classification (ASJC) codes

Software
Computer Graphics and Computer-Aided Design

Access to Document

https://doi.org/10.1109/MCG.2012.90

Cite this

@article{46ba2095c0954b92b859acb113d99e22,

title = "Garment personalization via identity transfer",

abstract = "A new system provides a virtual experience akin to trying on clothing. It clones the user's photographic image into a catalog of images of models wearing the desired garments. Simple offline training extracts the user's head. Segmentation accurately separates the face, hair, and background, employing both a three-kernel statistical model and graph cuts. The system adjusts the resulting image's skin color according to a statistical model and relights the head via spherical harmonics. Finally, using a parametric model, the system warps the clone's body dimensions to fit the user's dimensions. This creates high-quality compositions of the user's image and the given garment.",

keywords = "computer graphics, image enhancement, online cloning, photo processing",

author = "Roy Shilkrot and Daniel Cohen-Or and Ariel Shamir and Ligang Liu",

year = "2013",

doi = "https://doi.org/10.1109/MCG.2012.90",

language = "الإنجليزيّة",

volume = "33",

pages = "62--72",

journal = "IEEE Computer Graphics and Applications",

issn = "0272-1716",

number = "4",

}

TY - JOUR

T1 - Garment personalization via identity transfer

AU - Shilkrot, Roy

AU - Cohen-Or, Daniel

AU - Shamir, Ariel

AU - Liu, Ligang

PY - 2013

Y1 - 2013

N2 - A new system provides a virtual experience akin to trying on clothing. It clones the user's photographic image into a catalog of images of models wearing the desired garments. Simple offline training extracts the user's head. Segmentation accurately separates the face, hair, and background, employing both a three-kernel statistical model and graph cuts. The system adjusts the resulting image's skin color according to a statistical model and relights the head via spherical harmonics. Finally, using a parametric model, the system warps the clone's body dimensions to fit the user's dimensions. This creates high-quality compositions of the user's image and the given garment.

AB - A new system provides a virtual experience akin to trying on clothing. It clones the user's photographic image into a catalog of images of models wearing the desired garments. Simple offline training extracts the user's head. Segmentation accurately separates the face, hair, and background, employing both a three-kernel statistical model and graph cuts. The system adjusts the resulting image's skin color according to a statistical model and relights the head via spherical harmonics. Finally, using a parametric model, the system warps the clone's body dimensions to fit the user's dimensions. This creates high-quality compositions of the user's image and the given garment.

KW - computer graphics

KW - image enhancement

KW - online cloning

KW - photo processing

UR - http://www.scopus.com/inward/record.url?scp=84880833894&partnerID=8YFLogxK

U2 - https://doi.org/10.1109/MCG.2012.90

DO - https://doi.org/10.1109/MCG.2012.90

M3 - مقالة

SN - 0272-1716

VL - 33

SP - 62

EP - 72

JO - IEEE Computer Graphics and Applications

JF - IEEE Computer Graphics and Applications

IS - 4

M1 - 6253188

ER -

Garment personalization via identity transfer

Abstract

Keywords

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this