We study the task to infer and to track the viewpoint onto a 3D rigid object by observing its image contours in a sequence of images. To this end, we consider the manifold of invariant planar contours and learn the low-dimensional submanifold corresponding to the object contours by observing the object off-line from a number of different viewpoints. This submanifold of object contours can be parametrized by the view sphere and, in turn, be used for keeping track of the object orientation relative to the observer, through interpolating samples on the submanifold in a geometrically proper way. Our approach replaces explicit 3D object models by the corresponding invariant shape submanifolds that are learnt from a sufficiently large number of image contours, and is applicable to arbitrary objects.