This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Linear Object Classes and Image Synthesis From a Single Example Image
July 1997 (vol. 19 no. 7)
pp. 733-742

Abstract—The need to generate new views of a 3D object from a single real image arises in several fields, including graphics and object recognition. While the traditional approach relies on the use of 3D models, we have recently introduced [1], [2], [3] simpler techniques that are applicable under restricted conditions. The approach exploits image transformations that are specific to the relevant object class, and learnable from example views of other "prototypical" objects of the same class.

In this paper, we introduce such a technique by extending the notion of linear class proposed by Poggio and Vetter. For linear object classes, it is shown that linear transformations can be learned exactly from a basis set of 2D prototypical views. We demonstrate the approach on artificial objects and then show preliminary evidence that the technique can effectively "rotate" high-resolution face images from a single 2D view.

[1] D. Beymer and T. Poggio, “Face Recognition from One Example View,” Proc. Int'l Conf. Computer Vision, pp. 500-507, 1995.
[2] D. Beymer, A. Shashua, and T. Poggio, "Example-Based Image Analysis and Synthesis," A.I. Memo No. 1,431, Artificial Intelligence Laboratory, MIT, 1993.
[3] T. Poggio and R. Brunelli, "A Novel Approach to Graphics," Technical Report 1,354, MIT Media Laboratory Perceptual Computing Section, 1992.
[4] P. Kalocsai, I. Biederman, and . Cooper, "To What Extent Can the Recognition of Unfamiliar Faces Be Accounted For by a Representation of the Direct Output of Simple Cell," Ann. Meeting of the Assn. for Research in Vision and Ophthalmology,Sarasota, Fla., 1994.
[5] N. Troje and H. Bülthoff, "Face Recognition Under Varying Pose: The Role of Texture and Shape," Vision Research, vol. 36, no. 12, pp. 1,761-1,771, 1995.
[6] T. Poggio and T. Vetter, "Recognition and Structure From One 2D Model View: Observations on Prototypes, Object Classes, and Symmetries," A.I. Memo No. 1,347, Artificial Intelligence Laboratory, MIT, 1992.
[7] P. Schyns and H. Bülthoff, "Sparse Observations on Cortical Mechanisms For Object Recognition and Learning," A.I. Memo No. 1,404, Artificial Intelligence Laboratory, MIT, 1993.
[8] T. Vetter, T. Poggio, and H. Bülthoff, "The Importance of Symmetry and Virtual Views in Three-Dimensional Object Recognition," Current Biology, vol. 4, pp. 18-23, 1994.
[9] T. Cootes, C. Taylor, D. Cooper, and J. Graham, "Active Shape Models—Their Training and Application," Computer Vision and Image Understanding, vol. 61, pp. 38-59, 1995.
[10] D. Beymer, "Vectorizing Face Images by Interleaving Shape and Texture Computations," to appear as A.I. Memo, Artificial Intelligence Laboratory, MIT, 1995.
[11] M. Jones and T. Poggio, "Model-Based Matching of Line Drawings by Linear Combination of Prototypes," Proc. 5th Int'l Conf. Computer Vision, 1995.
[12] T. Beier and S. Neely, "Feature-Based Image Metamorphosis," Proc. SIGGRAPH "92,Chicago, Ill., pp. 35-42, 1992.
[13] J. Bergen and E. Adelson, "Hierarchical, Computationally Efficient Motion Estimation Algorithm," J. Opt. Soc. Am. A, vol. 4, p. 35, 1987.
[14] J. Bergen and R. Hingorani, "Hierarchical Motion-Based Frame Rate Conversion," Technical Report, David Sarnoff Research Center, Princeton, N.J., 1990.
[15] A. Hurlbert and T. Poggio, "Synthetizing a Color Algorithm From Examples," Science, vol. 239, pp. 482-485, 1988.
[16] G. Wolberg, Image Warping.Los Alamitos Calif.: CS Press, 1990.
[17] S. Ullman and R. Basri, "Recognition by Linear Combinations of Models," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, pp. 992-1006, 1991.
[18] D. Beymer, "Face Recognition Under Varying Pose," A.I. Memo No. 1,461, Artificial Intelligence Laboratory, MIT, 1993.
[19] T. Vetter and T. Poggio, "Symmetric 3D Objects Are an Easy Case for 2D Object Recognition," Spatial Vision, vol. 8, no. 4, pp. 443-453, 1994.

Index Terms:
3D object recognition, rotation invariance, deformable templates, image synthesis.
Citation:
Thomas Vetter, Tomaso Poggio, "Linear Object Classes and Image Synthesis From a Single Example Image," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 733-742, July 1997, doi:10.1109/34.598230
Usage of this product signifies your acceptance of the Terms of Use.