Extracting 3D facial animation parameters from multiview video clips

I-Chen Lin*, Jeng Sheng Yeh, Ming Ouhyoung

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

28 Scopus citations


An accurate and inexpensive procedure that estimates 3D facial motion parameters from mirror-reflected multiview video clips was proposed. A closed-form linear algorithm to reconstruct 3D positions from real versus mirrored point correspondences in an uncalibrated environment is also presented. Analysis showed that using mirror yields more accurate 3D position estimation than general-purpose stereovision approaches.

Original languageEnglish
Pages (from-to)72-80
Number of pages9
JournalIEEE Computer Graphics and Applications
Issue number6
StatePublished - 1 Nov 2002


Dive into the research topics of 'Extracting 3D facial animation parameters from multiview video clips'. Together they form a unique fingerprint.

Cite this