“…A growing line of research revolves around reconstructing the 3D geometry of the face and employing this information in further ad-hoc steps, as we do in this work. Some attempts on 3D face reconstruction [11], [12], [13], known as Shape From Shading, work on approximating the image formation process and postulate simplified assumptions about the lighting and illumination models leading to the formation of the image, while others, known as Structure from Motion (SfM), capitalise on the geometric constraints in multiple images of the same object to approach the reconstruction task [14], [15], [16]. 3D Morphable Models (3DMMs) have been researched and used substantially in the literature since the pioneering work of Blanz and Vetter [17], with many extensions [18], [19], [20].…”