Mirror MoCap: Automatic and efficient capture of dense 3D facial motion parameters from video

I-Chen Lin*, Ming Ouhyoung

*Corresponding author for this work

Research output: Contribution to journalArticle

27 Scopus citations

Abstract

In this paper, we present an automatic and efficient approach to the capture of dense facial motion parameters, which extends our previous work of 3D reconstruction from mirror-reflected multiview video. To narrow search space and rapidly generate 3D candidate position lists, we apply mirrored-epipolar bands. For automatic tracking, we utilize spatial proximity of facial surfaces and temporal coherence to find the best trajectories and rectify statuses of missing and false tracking. More than 300 markers on a subject's face are tracked from video at a process speed of 9.2 frames per second (fps) on a regular PC. The estimated 3D facial motion trajectories have been applied to our facial animation system and can be used for facial motion analysis.

Original languageEnglish
Pages (from-to)355-372
Number of pages18
JournalVisual Computer
Volume21
Issue number6
DOIs
StatePublished - 1 Jul 2005

Keywords

  • Automatic tracking
  • Facial animation
  • Facial animation parameters
  • Motion capture

Fingerprint Dive into the research topics of 'Mirror MoCap: Automatic and efficient capture of dense 3D facial motion parameters from video'. Together they form a unique fingerprint.

  • Cite this