Abstract

Appearance matching was recently demonstrated as a robust and eficient approach to 30 object recognition and pose estimation. Each object is represented as a continuous appearance manifold in a low-dimensional subspace parametrized by object pose and illumination direction. Here, the structural properties of appearance manifolds are analyzed with the aim of making appearance representation eficient in off-line computation, storage requirements, and on-line recognition time. In particular, the effect of illumination on the structure of the appearance manifold is studied. It is shown that for an ideal diffuse surface of arbitrary texture, the appearance manifold is linear and of dimensionality 3. This enables the construction of the entire illumination manifold

Citations