Adaptive Deformable Models for Graphics and Vision†
Siome Goldenstein
Instituto de Computação - Universidade Estadual de Campinas - Caixa Postal 6176, 13083-971, Campinas, SP, Brasil [email protected]
Search for more papers by this authorChristian Vogler
Gallaudet Research Institute - Gallaudet University - 800 Florida Ave. NE, Washington DC, USA 20002-3695 [email protected]
Search for more papers by this authorLuiz Velho
IMPA–Instituto de Matemática Pura e Aplicada - Estrada Dona Castorina, 110, 22460 Rio de Janeiro, RJ, Brasil [email protected]
Search for more papers by this authorSiome Goldenstein
Instituto de Computação - Universidade Estadual de Campinas - Caixa Postal 6176, 13083-971, Campinas, SP, Brasil [email protected]
Search for more papers by this authorChristian Vogler
Gallaudet Research Institute - Gallaudet University - 800 Florida Ave. NE, Washington DC, USA 20002-3695 [email protected]
Search for more papers by this authorLuiz Velho
IMPA–Instituto de Matemática Pura e Aplicada - Estrada Dona Castorina, 110, 22460 Rio de Janeiro, RJ, Brasil [email protected]
Search for more papers by this authorBased on “Adaptive Deformable Models”, by S. Goldenstein, C. Vogler and L. Velho, which appeared in Proceedings of SIBGRAPI/SIACG 2004 (ISBN 0-77=695-2227-0). © 2004 IEEE.
ABSTRACT
Deformable models are a powerful tool in both computer graphics and computer vision. The description and implementation of the deformations have to be simultaneously flexible and powerful, otherwise the technique may not satisfy the requirements of all the distinct applications. In this paper, we introduce a new method for the deformable model specification: deformable fields. Deformable fields are conceptually simple, lead to an easy implementation, and are suitable for adaptive models. We apply our new technique to describe an adaptive deformable face, and compare three different adaptation strategies. We show how our technique is suitable to describe different individuals, how to construct a model based on information from a single image, and how it allows the tracking of the deformation parameters over a video sequence.
References
- 1 V. Blanz, C. Basso, T. Poggio and T. Vetter. Reanimating faces in images and video. In Proceedings of EUROGRAPHICS, 2003.
- 2 R. Bowden, T. Mitchell and M. Sahardi. Real-time dynamic deformable meshes for volumetric segmentation and visualization. In Proc. BMVC 11, pp. 310–1319, 1997.
- 3 V. Blanz and T. Vetter. A morphable model for the synthesis of 3D faces. In SIGGRAPH pp. 187–194, August 1999.
- 4 G. Bishop and G. Welch. An introduction to the kalman filter. In SIGGRAPH 2001 Course Notes, 2001.
- 5 M. Dimitrijevic, S. Ilic and P. Fua. Accurate face models from uncalibrated and ill-lit video sequences. In Proc. of IEEE Computer Vision and Pattern Recognition, pp. 1034–1041, 2004.
- 6 D. DeCarlo, D. Metaxas and M. Stone. An anthropometric face model using variational techniques. In SIGGRAPH pp. 67–74, 1998.
- 7 L. Floriani, P. Magillo and E. Puppo. Efficient implementation of multi-triangulations. In IEEE Visualization '98, D. Ebert, H. Hagen, H. Rushmeier, Eds., pp. 43–50, 1998.
- 8 P. Fua. Regularized bundle-adjustment to model heads from image sequences. International Journal of Computer Vision, 38(2): 153–171, 2000.
- 9 M. Garland. Multiresolution modeling: Survey & future opportunities. In Eurographics '99, State of the Art Report (STAR), 1999.
- 10 X. Gu, S. Gortler and H. Hoppe. Geometry images. In SIGGRAPH pp. 355–361, 2002.
- 11 S. Goldenstein. A gentle introduction to predictive filters. Revista de Informatica Teorica e Aplicada RITA XI, 1, 61–89, 2004.
- 12 N. Gordon, D. Salmon and A. Smith. A novel approach to nonlinear/nonGaussian bayesian state estimation. In IEEE Proc. Radar Signal Processing, vol. 140, pp. 107–113, 1993.
- 13 S. Goldenstein, C. Vogler and D. Metaxas. Directed acyclic graph representation of deformable models. In Proc. of IEEE workshop on motion and video computing, 2002.
- 14 S. Goldenstein, C. Vogler and D. Metaxas. Statistical cue integration in DAG deformable models. In IEEE Trans. on Pattern Analysis and Machine Intelligence 25 vol. 7, July 2003.
- 15 S. Goldenstein, C. Vogler and D. Metaxas. 3D facial tracking from corrupted movie sequences. In Proc. of IEEE Computer Vision and Pattern Recognition, 2004.
- 16 H. Hoppe. Efficient implementation of progressive meshes. Computers & Graphics 22, 1, pp. 27–36, 1998.
- 17 M. Isard and A. Blake. CONDENSATION: conditional density propagation for visual tracking. International Journal of Computer Vision 29, 1, 5–28, 1998.
- 18
L. Kobbelt,
T. Bareuther and
H. Seidel.
Multiresolution shape deformations for meshes with dynamic vertex connectivity.
Computer Graphics Forum
19, 3, 2000.
10.1111/1467-8659.00417 Google Scholar
- 19 M. Kass, A. Witkin and D. Terzopoulos. Snakes: Active Contour Models. International Journal of Computer Vision 1 321–331, 1988.
- 20 W. B. R. Lickorish. Simplicial moves on complexes and manifolds. In Proceedings of the Kirbyfest vol. 2, pp. 299–320, 1999.
- 21 P. Maybeck. Stochastic Models, Estimation, and Control. Academic Press, New York , 1979.
- 22 H. Murase and S. K. Nayar. Visual learning and recognition of 3-D objects from appearance. International Journal of Computer Vision 14, 5–24, 1995.
- 23 F. Pighin, J. Hecker, D. Lischinski, R. Szeliski and D. Salesin. Synthesizing realistic facial expressions from photographs. In SIGGRAPH, pp. 75–84, 1998.
- 24 F. Pighin, R. Szeliski and D. Salesin. Modeling and animating realistic faces from images. International Journal of Computer Vision 50, 2, 143–169, 2002.
- 25 P. J. Rousseeuw and K. V. Driessen. A fast algorithm for the minimum covariance determinant estimator. Technometrics 41, 212–223, 1999.
- 26 A. Romdhani and T. Vetter. Efficient, robust and accurate fitting of a 3D morphable model. In Proc. of Intl. Conf. of Computer Vision, pp. 59–66, 2003.
- 27 A. Smith and A. Gelfand. Bayesian statistics without tears: A sampling-resampling perspective. American Statistician 46, 2, 84–88, 1992.
- 28 D. Samaras, D. Metaxas, P. Fua and Y. Leclerc. Variable albedo surface reconstruction from stereo and shape from shading. In Proc. of IEEE Computer Vision and Pattern Recognition, pp. 480–487, 2000.
- 29 J. Shi and C. Tomasi. Good features to track. In Proc. of IEEE Computer Vision and Pattern Recognition, pp. 593–600, 1994.
- 30 H. Tao and T. Huang. Visual estimation and compression of facial motion parameters: elements of a 3D model-mased video coding system. International Journal of Computer Vision 50, 2, 111–125, 2002.
- 31 B. Von Herzen and A. H. Barr. Accurate triangulations of deformed, intersecting surfaces. In Computer Graphics SIGGRAPH '87 Proceedings, vol. 21, pp. 103–110, July 1987.
- 32 L. Velho and J. Gomes. Variable resolution 4-k meshes: Concepts and applications. Computer Graphics forum 19, 195–212, 2000.
- 33 C. Vogler, S. Goldenstein, J. Stolfi, V. Pavlovic and D. Metaxas. Outlier rejection in high-dimensional deformable models. Image and Vision Computing, 2005 (in press).
- 34
A. Witkin,
M. Gleicher and
W. Welch.
Interactive dynamics.
Computer Graphics, vol. 24, pp. 11–21, 1990
10.1145/91394.91400 Google Scholar
- 35 Z. Wen and T. Huang. Capturing subtle facial motions in 3D face tracking. In Proc. of Intl. Conf. of Computer Vision, pp. 1343–1350, 2003.
