Abstract

Described herein is a technique for creating a 3D face model using images obtained from an inexpensive camera associated with a general-purpose computer. Two still images of the user are captured, and two video sequences. The user is asked to identify five facial features, which are used to calculate a mask and to perform fitting operations. Based on a comparison of the still images, deformation vectors are applied to a neutral face model to create the 3D model. The video sequences are used to create a texture map. The process of creating the texture map references the previously obtained 3D model to determine poses of the sequential video images.

Other References

• Soon-Cang Pei et al., Global Motion Estimation in Model-Based Image Coding by Tracking Three-Dimensional Contour Featu Points, IEEE 1051-8215/98, 181-190.*
• Pighin et al., Resynthesizing facial animation through 3D model-tracking, IEEE Inspec Accession No. 6371194, 1-8.*
• Shakunaga et al., Integration of eigentemplate and structure matching for automatic facial feature detection, IEEE Inspec Accession No. 5920393, 1-6.*
• Perlin, Reatme responsive animation with personality, IEEE 1071-2626/95, 5-15.*
• Skaria et al., Modeling subdivision control meshes for creating coorton faces, IEEE 0-7695-0853-7/01, 216-225.*
• Parke, Computer graphics models for the human face, IEEE CH515-6/79/0000-0724, 724-727.*
• Terzopoulos et al., Analysis of facial images using physical and anatomical models, IEEE CH2934-8/90/0000/072, 727-732.*
• DiPaola, FaceSpace: a facial spatial domain toolkit, IEEE 1093-9547, 1-5.*
• DeCarlo et al. An anthropometric face model using variational techniques, University of Pennsylvania, 1-8.*
• Blanz et al., Face recohgnition based on fitting a 3d morphable mode, IEEE 0162-8828/03, 1063-1074.*
• Zheng et al., 3D models from contours, IEEE 0-8186, 349-353.*
• Vetter et al., Linear object classes and image synthesis, IEEE 0162-8828/97, 733-741.*
• Dariush et al., Spatiotemporal analysis of face profiles, IEEE Inspec Accession No. 5920418, 248-253.*
• Akimoto et al., Automatic creation of 3D facial models, IEEE 0272-16/93, 16-22.*
• Faugeras “Three Dimensional Computer Vision”; 1999; pp. 1-663.
• Zhang; “A New Multistage Approach to Motion and Structure Estimation: From Essential Parameters to Euclidean Motion Via Fundamental Matrix”; Jun. 1996; pp. 1-38.
• More; “The Levenberg-Marquardt Algorithm: Implentation and Theory”; 1978; pp. 105-116.
• Jebara et al; “Parametrized Structure from Motion for 3D Adaptive Feedback Tracking of Faces”; 1997, pp. 144-150.
• Fua; “Using Model-Driven Bundle-Adjustment to Model Heads from Raw Video Sequence”; pp. 1-8.
• Zhang; “On sthe Optimization Criteria Used in Two-View Motion Analysis”; Jul. 1998; pp. 717-729.
• Pighin et al; “Synthesizing Realistic Facial Expressions from Photographs”; pp. 1-20.
• Fua et al; “From Regular Images to Animated Heads: A Least Squares Approach”; pp. 1-15.
• Kang et al; “Appearance-based Structure from Motion Using Linear Classes of 3-D Models”; pp. i-ii, 1-32.