Multidimensional Morphable Models

We describe a exible model for representing images of objects of a certain class, known a priori, such as faces, and introduce a new algorithm for matching it to a novel image and thereby performing image analysis. We call this model a multidimensional morphable model or just a morphable model. The morphable model is learned from example images (called prototypes) of objects of a class. In this paper we introduce an e ective stochastic gradient descent algorithm that automatically matches a model to a novel image by nding the parameters that minimize the error between the image generated by the model and the novel image. Two examples demonstrate the robustness and the broad range of applicability of the matching algorithm and the underlying morphable model. Our approach can provide novel solutions to several vision tasks, including the computation of image correspondence, object veri cation, image synthesis and image compression.

• Type: Conference
• Year: 1998
• Where: ICCV
• Authors: Michael J. Jones, Tomaso Poggio
• Keywords: Computer Vision, Exible Model, Gradient Descent Algorithm, ICCV 1998, Image Correspondence, Morphable Model, Multidimensional Morphable Model