Image synthesis from a single example image
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 exploit 2D image transformations that are specific to the relevant object class and learnable from example views of other “prototypical” objects of the same class.
For linear object classes we show 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.
Index Items3D Object recognition rotation invariance deformable models image synthesis
Unable to display preview. Download preview PDF.
- 1.N. Troje and H. Bülthoff, “Face recognition under varying pose: The role of texture and shape,” Vision Research in press.Google Scholar
- 2.T. Poggio and T. Vetter, “Recognition and structure from one 2D model view: observations on prototypes, object classes, and symmetries,” A.I. Memo No. 1347, Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 1992.Google Scholar
- 3.M. Jones and T. Poggio, “Model-based matching of line drawings by linear combination of prototypes,” in ICCV'95, 1995.Google Scholar
- 4.D. Beymer and T. Poggio, “Face recognition from one model view,” in ICCV'95, 1995.Google Scholar
- 5.T. Poggio and R. Brunelli, “A novel approach to graphics,” Technical report 1354, MIT Media Laboratory Perceptual Computing Section, 1992.Google Scholar
- 6.D. Beymer, A. Shashua, and T. Poggio, “Example-based image analysis and synthesis,” A.I. Memo No. 1431, Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 1993.Google Scholar
- 7.J. Bergen, P. Anandan, K. Hanna, and R. Hingorani, “Hierarchical model-based motion estimation,” in Proceedings of the European Conference on Computer Vision, (Santa Margherita Ligure, Italy), pp. 237–252, 1992.Google Scholar
- 8.J. Bergen and R. Hingorani, “Hierarchical motion-based frame rate conversion,” technical report, David Sarnoff Research Center Princeton NJ 08540, 1990.Google Scholar
- 9.G. Wolberg, Image Warping. Los Alamitos CA: IEEE Computer Society Press, 1990.Google Scholar
- 10.S. Ullman and R. Basri, “Recognition by linear combinations of models.,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, pp. 992–1006, 1991.Google Scholar