Share Email Print

Proceedings Paper

Realistic texture extraction for 3D face models robust to self-occlusion
Author(s): Chengchao Qu; Eduardo Monari; Tobias Schuchert; Jürgen Beyerer
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In the context of face modeling, probably the most well-known approach to represent 3D faces is the 3D Morphable Model (3DMM). When 3DMM is fitted to a 2D image, the shape as well as the texture and illumination parameters are simultaneously estimated. However, if real facial texture is needed, texture extraction from the 2D image is necessary. This paper addresses the possible problems in texture extraction of a single image caused by self-occlusion. Unlike common approaches that leverage the symmetric property of the face by mirroring the visible facial part, which is sensitive to inhomogeneous illumination, this work first generates a virtual texture map for the skin area iteratively by averaging the color of neighbored vertices. Although this step creates unrealistic, overly smoothed texture, illumination stays constant between the real and virtual texture. In the second pass, the mirrored texture is gradually blended with the real or generated texture according to the visibility. This scheme ensures a gentle handling of illumination and yet yields realistic texture. Because the blending area only relates to non-informative area, main facial features still have unique appearance in different face halves. Evaluation results reveal realistic rendering in novel poses robust to challenging illumination conditions and small registration errors.

Paper Details

Date Published: 27 February 2015
PDF: 9 pages
Proc. SPIE 9405, Image Processing: Machine Vision Applications VIII, 94050P (27 February 2015); doi: 10.1117/12.2079924
Show Author Affiliations
Chengchao Qu, Karlsruher Institut für Technologie (Germany)
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung (Germany)
Eduardo Monari, Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung (Germany)
Tobias Schuchert, Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung (Germany)
Jürgen Beyerer, Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung (Germany)
Karlsruher Institut für Technologie (Germany)

Published in SPIE Proceedings Vol. 9405:
Image Processing: Machine Vision Applications VIII
Edmund Y. Lam; Kurt S. Niel, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?