Skip to main navigation Skip to search Skip to main content

Single-View Dressed Human Modeling via Morphable Template

  • Lin Wang
  • , Kai Jiang
  • , Bin Zhou
  • , Qiang Fu
  • , Kan Guo
  • , Xiaowu Chen*
  • *Corresponding author for this work
  • Beihang University
  • Science China Press

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We introduce a morph able template for dressed human modeling, called Morph able Dressed Human (MDH) template. The template is obtained by learning basic functions from two common types of clothes (long shirts and trousers) and defining a deform-combine manipulation. Our MDH template is parametric, spans variation in both clothes and body/pose, and can generate various dressed human shapes. The template can be morphed to perform dressed human modeling from just a single image through shape fitting and deformation/texture transfer. We demonstrate the effectiveness of our MDH template in single-view dressed human estimation and garment transfer.

Original languageEnglish
Title of host publicationProceedings - 2014 International Conference on Virtual Reality and Visualization, ICVRV 2014
EditorsXukun Shen, Xiaopeng Zhang, Zhong Zhou, Guodong Zhang, Xun Luo
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages138-145
Number of pages8
ISBN (Electronic)9781479968541
DOIs
StatePublished - 28 Sep 2015
EventInternational Conference on Virtual Reality and Visualization, ICVRV 2014 - Shenyang, China
Duration: 30 Aug 201431 Aug 2014

Publication series

NameProceedings - 2014 International Conference on Virtual Reality and Visualization, ICVRV 2014

Conference

ConferenceInternational Conference on Virtual Reality and Visualization, ICVRV 2014
Country/TerritoryChina
CityShenyang
Period30/08/1431/08/14

Keywords

  • Human modeling
  • Morphable model
  • Single image

Fingerprint

Dive into the research topics of 'Single-View Dressed Human Modeling via Morphable Template'. Together they form a unique fingerprint.

Cite this