Depth Estimation with Light Field and Photometric Stereo Data Using Energy Minimization

Through the fusion of light fields and photometric stereo, two state-of-the-art computational imaging approaches, we improve the 3D reconstruction of objects. Light field imaging techniques observe a scene from different angles, which results in a strong absolute depth estimation of the scene. Photometric stereo uses multiple illuminations to reconstruct the surface of objects, which allows estimating fine local details of objects, even when no surface structure is present. We combine both approaches within a minimization algorithm, which exhibits an accurate absolute depth with a high sensitivity to fine surface details.