Abstract
This paper presents a working system for building 3-D human face models from two photographs. Rather than using expensive 3-D scanners, we show that frontal face models can be faithfully reconstructed from two photographs taken by consumer digital cameras in a totally non-invasive setup. We first rectify the image pair so that corresponding epipolar lines become coincident, by computing a dual point transformation. We then address the correspondence problem by converting it into a maximal surface extraction problem, which is then solved efficiently. The method effectively removes local extrema. Finally, a Euclidean reconstruction is achieved with the help of a novel factorization method for perspective cameras. Most of the computational steps are conducted in projective space. Euclidean information is introduced only at the last stage. This sets apart our system from the traditional ones which begin with metric information by using carefully calibrated cameras. We have collected a bank of face pairs to test our system, and are satisfied with its performance. Results from this image database are demonstrated.
Similar content being viewed by others
References
R. Raskar, G. Welch, M. Cutts, A. Lake, L. Stesin, and H. Fuchs, “The Office of the Future: A Unified Approach to Image-Based Modelling and Spatially Immersive Displays, ” in Proc.ACM SIGGRAPH '98, 1998, pp. 179–188.
Web site, National Tele-Immersion Initiative, http://io-advanced. org/tele-immersion/cubenet.html.
O. Faugeras, Three-Dimensional Computer Vision-A Geometric Viewpoint, Cambridge, Massachusetts: MIT Press, 1993.
Z. Zhang, R. Deriche, Q.-T Luong, and O. Faugeras, “A Ro-bust Approach to Image Matching: Recovery of the Epipolar Geometry, ” in Proc.Int'l Symposium of Young Investigators on Information-Computer-Control, Beijing, China, 1994, pp. 7–28.
Q. Chen and G. Medioni, “A Volumetric Stereo Matching Method: Application to Image-Based Modelling, ” in Proc.Com-puter Vision and Pattern Recognition'99, 1999, vol. I, pp. 29–34.
Q. Chen and G. Medioni, “Efficient, Iterative Solution to M-View Projective Reconstruction Problem, ” in Proc.Computer Vision and Pattern Recognition'99, 1999, vol. II, pp. 55–61.
C.J. Poelman and T. Kanade, “A Paraperspective Factorization Method for Shape and Motion Recovery, ” IEEE T.Pattern Analysis and Machine Intelligence, vol. 19, no. 3, 1997, pp. 206–218.
S.T. Barnard and M.A. Fischler, “Computational Stereo, ” Surveys, vol. 14, no. 4, 1982, pp. 553–572.
U. Dhond and J. Aggarwal, “Structure from Stereo-A Review, ” IEEE T.Systems, Man and Cybernetics, vol. 19, no. 6, 1989, pp. 1489–1510.
Y. Ohta and T. Kanade, “Stereo by Intra-and Inter-Scanline Search Using Dynamic Programming, ” IEEE T.Pattern Analysis and Machine Intelligence, vol. 7, no. 2, 1985, pp. 139–154.
G.-Q. Wei, W. Brauer, and G. Hirzinger, “Intensity-and Gradient-Based Stereo Matching Using Hierarchical Gaussian Basis Functions, ” IEEE T.Pattern Analysis and Machine Intelligence, vol. 20, no. 11, 1998, pp. 1143–1160.
W. Hoff and N. Ahuja, “Surfaces from Stereo: Integrating Fea-ture Matching, Disparity Estimation, and Contour Detection, ” IEEE T.Pattern Analysis and Machine Intelligence, vol. 11, no. 2, 1989, pp. 121–136.
M.-S. Lee and G. Medioni, “Inferring Segmented Surface De-scription from Stereo Data, ” in Proc.Computer Vision and Pat-tern Recognition'98, 1998, pp. 347–352.
C.K. Tang and G. Medioni, “Integrated Surface, Curve and Junc-tion Inference from Sparse 3-D Data Sets, ” IEEE T.Pattern Analysis and Machine Intelligence, vol. 20, no. 11, 1998, pp. 1206–1223.
H. Ishikawa and D. Geiger, “Occlusions, Discontinuities, and Epipolar Lines in Stereo, ” in Proc.European Conf.on Computer Vision '98, 1998.
S. Roy and I.J. Cox, “A Maximum-Flow Formulation of the N-camera Stereo Correspondence Problem, ” in Proc.Int'l Conf.on Computer Vision '98, 1998, pp. 492–499.
H. Horace, S. Ip, and L. Yin, “Constructing a 3D Individualized Head Model from Two Orthogonal Views, ” Visual Computer, vol. 12, 1996, pp. 254–266.
F. Pighin, J. Hecker, D. Lischinski, R. Szeliski, and D. Salesin, “Synthesizing Realistic Facial Expressions From Photographs, ” in Proc.ACM SIGGRAPH '98, 1998, pp. 75–84.
Web site, 3D Construction Company, http://www. 3dconstruction.com.
Web site, Eos Systems Inc., http://www.photomodeler.com.
O. Faugeras, “Stratification of 3-D Vision: Projective, Affine, and Metric Representations, ” Journal of the Optical Society of America A, vol. 12, no. 3, 1995, pp. 465–484.
J.L. Mundy and A. Zisserman, Geometric Invariance in Computer Vision, Cambridge, MA: MIT Press, 1992.
W. Lorensen and H. Cline, “Marching Cubes: A High-Resolution 3D Surface Construction Algorithm, ” in Proc.ACM SIGGRAPH’ 87, 1987, pp. 163–169.
T. Itoh and K. Koyamada, “Automatic Iso-surface Propagation Using an Extrema Graph and Sorted Boundary Cell Lists, ” IEEE T.Visualization and Computer Graphics, vol. 1, no. 4, 1995, pp. 319–327.
I. Cox, S. Hingorani, S. Rao, and B. Maggs, “A Maximum-Likelihood Stereo Algorithm, ” Computer Vision and Image Understating, vol. 63, no. 3, 1996, pp. 542–567.
A. Tomasi and T. Kanade, “Shape and Motion from Image Streams Under Orthography: A Factorization Method, ” Int'l J.Computer Vision, vol. 9, no. 2, 1992, pp. 137–154.
Q. Luong and T. Viéville, “Canonic Representations for the Geometries of Multiple Projective Views, ” in Proc.European Conference on Computer Vision '94, 1994, pp. 589–596.
Q. Chen and G. Medioni, “A Semiautomatic System to Infer Complex 3-D Shapes from Photographs, ” in Proc.IEEE Multi-media Systems '99, 1999, vol. II, pp. 798–805.
P. Burt and B. Julesz, “A Disparity Gradient Limit for Binocular Fusion, ” Perception, vol. 9, 1980, pp. 671–682.
B. Guenter, C. Grimm, D. Wood, H. Malvar, and F. Pighin, “Making Faces, ” in Proc.ACM SIGGRAPH '98, 1998, pp. 55–66.
M. Pollefeys, R. Koch, and L.V. Gool, “Self-Calibration and Metric Reconstruction in Spite of Varing and Unknown Internal Camera Parameters, ” in Proc.Int'l Conf.Computer Vision '98, 1998, pp. 90–95.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Chen, Q., Medioni, G. Building 3-D Human Face Models from Two Photographs. The Journal of VLSI Signal Processing-Systems for Signal, Image, and Video Technology 27, 127–140 (2001). https://doi.org/10.1023/A:1008131816432
Published:
Issue Date:
DOI: https://doi.org/10.1023/A:1008131816432