Abstract
We study the task to infer and to track the viewpoint onto a 3D rigid ob ject by observing its image contours in a sequence of im- ages. To this end, we consider the manifold of invariant planar contours and learn the low-dimensional submanifold corresponding to the ob ject contours by observing the ob ject off-line from a number of different view- points. This submanifold of ob ject contours can be parametrized by the view sphere and, in turn, be used for keeping track of the ob ject ori- entation relative to the observer, through interpolating samples on the submanifold in a geometrically proper way. Our approach replaces ex- plicit 3D ob ject models by the corresponding invariant shape submani- folds that are learnt from a sufficiently large number of image contours, and is applicable to arbitrary ob jects.