Mobile face capture for virtual face videos

Chandan K. Reddy, George C. Stockman, Jannick P. Rolland, Frank A. Biocca

Research output: Contribution to journalConference article

5 Scopus citations

Abstract

Minimally obtrusive face capture is essential for applications in tele-conferencing, collaborative work, and mobile applications. Acquiring and coding video for such applications is a challenging problem, particularly for a mobile user. A pilot head-mounted display system (HMD) is shown that captures two side views of the face and generates in real-time a quality frontal video of the wearer. The face is captured with little obstruction of the users field of view. The frontal views are generated by warping and blending the side views after a calibration step. In tests of a bench prototype, the generated virtual videos compared well with real video based on both objective and qualitative criteria. With success of the pilot work, we are continuing development of the mobile HMD system.

Original languageEnglish (US)
Article number1384870
JournalIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume2004-January
Issue numberJanuary
DOIs
StatePublished - Jan 1 2004
Event2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2004 - Washington, United States
Duration: Jun 27 2004Jul 2 2004

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Mobile face capture for virtual face videos'. Together they form a unique fingerprint.

  • Cite this