Skip to main navigation Skip to search Skip to main content

Data-Driven Hair Modeling from a Single Image

  • Jiqiang Wu
  • , Yongtang Bao*
  • , Yue Qi
  • *Corresponding author for this work
  • Beihang University
  • Shandong University of Science and Technology

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

Abstract

Hair is one of the most distinctive part of a human body, which is essential for the digitization of compelling virtual avatars. We present a data-driven approach for generating complete and complex 3D hairstyles from a single-view portrait. We construct a hairstyle database which contains more than 2000 hair models. Given a target hairstyle portrait image, we first draw a few strokes as guidance. We then search multiple best matching examples from the database based on our enhanced matching algorithm. Finally, we combine them consistently into a single hairstyle. The generated hairstyles are visually comparable to original portrait images. The reconstructed 3D hair models can be used for many applications, such as hair editing, and dynamic hair simulation.

Original languageEnglish
Title of host publicationProceedings - 8th International Conference on Virtual Reality and Visualization, ICVRV 2018
EditorsKai Xu, Bin Zhou, Xun Luo, Yanwen Guo
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages8-14
Number of pages7
ISBN (Electronic)9781538684979
DOIs
StatePublished - 2 Jul 2018
Event8th International Conference on Virtual Reality and Visualization, ICVRV 2018 - Qingdao, China
Duration: 22 Oct 201824 Oct 2018

Publication series

NameProceedings - 8th International Conference on Virtual Reality and Visualization, ICVRV 2018

Conference

Conference8th International Conference on Virtual Reality and Visualization, ICVRV 2018
Country/TerritoryChina
CityQingdao
Period22/10/1824/10/18

Keywords

  • Data-Driven
  • Hair modeling
  • Hairstyle database
  • Orientation field

Fingerprint

Dive into the research topics of 'Data-Driven Hair Modeling from a Single Image'. Together they form a unique fingerprint.

Cite this