| CPC G01B 11/303 (2013.01) [G06T 15/506 (2013.01)] | 15 Claims |

|
1. A method of determining a material property of an object, the method comprising:
obtaining a real light intensity value for each of a first number of light source positions and each of a second number of light sensor positions, the real light intensity value indicating an intensity of light from the light source position that is reflected or diffused by an object to the light sensor position;
determining a three-dimensional surface of the object; and
for each of a plurality of points on the three-dimensional surface of the object, using a model that has been trained by machine learning, predicting the material property for the object at the point based on the obtained real light intensity values,
wherein the material property comprises one or more of: specular reflection, roughness, diffuse light emission, sub-surface scattering, transparency, and index of refraction, and
wherein the model is a neural network configured to receive light intensity values, and their associated light source positions and light sensor positions, as an input layer, and to produce a representation of the material property, as an output layer.
|