Developing a multispectral photometric stereo system for acquiring high-fidelity surface normals

Abstract

Multispectral imaging has become more accessible as an advanced imaging technique for a physically-meaningful imaging spectroscopy, and photometric stereo has been commonly practiced for digitizing a 3D shape with simplicity for more than three decades. However, these two imaging techniques have rarely been combined as 3D imaging applications yet. Reconstructing the shape of a 3D object using photometric stereo is still challenging due to optical phenomena such as global illumination, specular reflection and self shadow. In addition, removing interreflection in photometric stereo is a traditional chicken-and-egg problem as we need to account for interreflection without knowing geometry. In this thesis, we present a novel multispectral photometric stereo method that allows us to remove interreflection on diffuse materials using multispectral reflectance information. We demonstrate several benefits of our multispectral photometric stereo method such as removing interreflection and reconstructing the 3D shapes of objects to a high accuracy.