A method of scanning a 3D object includes: receiving a user's input to perform a scanning operation via a user interface, and in response using a light projector, projecting structured light onto the surface of a physical object about target positions on the surface of the physical object; and recording a sequence of first images of at least a portion of the surface of the physical object including a light scatter region illuminated by the structured light being projected about the target positions on the surface of the physical object using a camera. A trained image processing network configured during training to output data comprising a representation of positions being estimates of the target positions on the surface of the physical object in response to receiving one or more first images can be used.