Garment personalization via identity transfer

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

Research output: Contribution to journalArticlepeer-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 languageEnglish
Article number6253188
Pages (from-to)62-72
Number of pages11
JournalIEEE Computer Graphics and Applications
Volume33
Issue number4
DOIs
StatePublished - 2013

Keywords

  • computer graphics
  • image enhancement
  • online cloning
  • photo processing

Fingerprint

Dive into the research topics of 'Garment personalization via identity transfer'. Together they form a unique fingerprint.

Cite this