Facial View Synthesis from a Single Image using Shape from Shading

We present a facial view synthesis technique based on explicit shape and reflectance information extracted from a single image. The technique combines an image based reflectance estimation process with a novel method of interpolating between needle-maps recovered using shape from shading. This allows images of a face to be synthesised under novel lighting, pose and skin reflectance given only one example image. We exploit facial symmetry by reflecting the needle-map of a rotated face to yield the needle-map of the face rotated in the opposite direction. This provides two needle-maps between which interpolation can be performed.