A system includes a processor configured to instruct image capture of a vehicle from a plurality of predefined perspectives, the perspectives defined to result in images providing a 360 degree capture of a vehicle surface. The processor is also configured to receive a plurality of images, at least one from each perspective, of a vehicle from a mobile device camera. The processor is further configured to build a 3-D model of the vehicle surface from the images and compare the 3-D model to a stored reference model of the vehicle surface in order to recognize damage to the vehicle.