Abstract Claims Description Full Text

Abstract

A memory based computer graphic animation system generates desired images and image sequences from 2-D views. The 2-D views provide sparse data from which intermediate views are generated based on a generalization and interpolation technique of the invention. This technique is called a Hyper Basis function network and provides a smooth mapping between the given set of 2-D views and a resulting image sequence for animating a subject in a desired movement. A multilayer network provides learning of such mappings and is based on Hyper Basis Functions (HBF's). A special case of the HBFs is the radial basis function technique used in a preferred embodiment. The invention generalization/integration technique involves establishing working axes along which different views of the subject are taken. Different points along the working axes define different positions (geometrical and/or graphical) of the subject. For each of these points, control points for defining a view of the subject are either given or calculated by interpolation/generalization of the present invention.

Other References

• Wilhelms; "Toward Automatic Motion Control", IEEE Computer Graphics and Applications 1987, vol. 7, No. 4, pp. 11-22
• Steketee et al, "Parametric KeyFrame Interpolation Incorporating Kinetic Adjustment and Phrasing Control", Computer Graphics, 1985, vol. 19, No. 3, pp. 255-262
• Sturman, "Interactive KeyFrame Animation of 3-D Articulated Models", Proceedings of Graphics Interface '84, 1984, pp. 35-40
• Burtnyk, Nestor et al., "Computer Assisted Film Animation," Bulletin of the Radio and Electrical Engineering Division, National Research Council of Canada, 20(3): pp. 8-12, (Sep. 1970)
• Wein, Marceli et al., "Computer Graphics and Film Animation," Bulletin of the Radio and Electrical Engineering Division, National Research Council of Canada, 19(2): pp. 39-42, (Apr. 1969)
• Burtnyk, Nestor et al., "Computer-Generated Key-Frame Animation," Journal of the Society of Motion Picture and Television Engineers, 80(3): pp. 149-153, (Mar. 1971)
• Wein, Marceli et al., "A Computer Facility for Film Animation and Music," Canadian Computer Conference Session, pp. 2122-2125, (Jun. 1971)
• Burtnyk, Nestor et al., "Towards a Computer Animating Production Tool," Eur Comput Congr Proc, pp. 171-185, (May 13-17, 1974)
• Burtnyk, Nestor et al., "Interactive Skeleton Techniques for Enhancing Motion Dynamics in Key Frame Animation," Communications of the ACM, 19(10): pp. 564-569, (Oct. 1976)
• Takeshi Agui et al., "Three Dimensional Computer Animation by Trigonometric Approximation to Aperiodic Motion," Systems and Computers in Japan, 19(5):82-88 (May 1988)
• Mark C. K. Yang et al., "Automatic Curve Fitting with Quadratic B-Spline Functions and Its Applications to Computer-Assisted Animation," Computer Vision, Graphics, and Image Processing, 33(3):346-363 (Mar. 1986)
• Henry Bortman, "The Future of Type?", MacUser (Jul. 1991): 187-195
• Peter Litwinowicz, "Inkwell: A 21/2-D Animation System", Computer Graphics, 25(4):113-121 (Jul. 1991)
• Tomaso Poggio et al., "A Theory of Networks for Approximation and Learning", AI Memo No. 1140, Artificial Intelligence Laboratory, MIT, Jul. 1989, pp. 1-84
• Tomaso Poggio et al., "Regularization Algorithms for Learning that are Equivalent to Multilayer Networks", Science, vol. 247, Feb. 23, 1990, pp. 978-982
• Tomaso Poggio et al., "Networks for Approximation and Learning", Proceedings of the IEEE, vol. 78, No. 9, Sep. 1990, pp. 1481-1497
• Tomaso Poggio et al., "A Network that Learns to Recognize Three Dimensional Objects", Nature, vol. 343, No. 6255, 1990, pp. 263-26