Data-driven shape-from-shading using curvature consistency

This paper makes two contributions to the problem of needle-map recovery using shape-from-shading. Firstly, we provide a geometric update procedure which allows the image irradiance equation to be satisfied as a hard-constraint. This improves the data-closeness of the recovered needle-map. Secondly, we consider how topographic constraints can be lured to impose local consistency on the recovered needle-map. We present several alternative curvature consistency models, and provide an experimental assessment of the new shape-from-shading framework on both real-world images and synthetic images with known ground-truth surface-normals. The main conclusion drawn from our analysis is that the new framework allows rapid development of more appropriate constraints on the SFS problem.