Appearance capture under ambient lighting conditions using a deep-learning neural network model

Abstract

A method is described which includes receiving a number of object images of an object. Each object image corresponds to a different view direction. First and second object images correspond to first and second directions. A mesh is determined corresponding to the target region of the object surface based on a first subset of the number of object images. Diffuse and specular maps are determined corresponding to the target region of the object surface based on processing a second subset of the object images using a deep learning neural network model trained to estimate diffuse and specular albedo components based on an input image. A tangent normal map is determined corresponding to the target region of the object surface based on high-pass filtering each object image of the second subset. The method also includes storing and/or outputting the mesh, the diffuse map, the specular map and the tangent normal map.