Viewpoint interpolation of face images using an ellipsoid model 


Vol. 32,  No. 6, pp. 572-578, Jun.  2007


PDF Full-Text
  Abstract

To establish eye contact in video teleconferencing, it is necessary to synthesize a front view image by viewpoint interpolation. We can find the viewing direction of a user, and interpolate an image seen from that viewpoint, which will result in a face image observed from the front. There are two categories of previous research: image based method and model based method. The former is simple to calculate, however, it shows limited performance for complex objects. And the latter is robust to noise while it is computationally expensive. We propose to approximate face images as ellipses and match them to build an ellipsoid and then synthesize a new image from a given virtual camera position. We show that it is simple and robust from various experiments.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

N. Yoon and B. Lee, "Viewpoint interpolation of face images using an ellipsoid model," The Journal of Korean Institute of Communications and Information Sciences, vol. 32, no. 6, pp. 572-578, 2007. DOI: .

[ACM Style]

Naree Yoon and Byung-Uk Lee. 2007. Viewpoint interpolation of face images using an ellipsoid model. The Journal of Korean Institute of Communications and Information Sciences, 32, 6, (2007), 572-578. DOI: .

[KICS Style]

Naree Yoon and Byung-Uk Lee, "Viewpoint interpolation of face images using an ellipsoid model," The Journal of Korean Institute of Communications and Information Sciences, vol. 32, no. 6, pp. 572-578, 6. 2007.

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880