Global Shape from Shading

摘要

A new approach for the reconstruction of a smooth three-dimensional object from its two-dimensional gray-level image is presented. An algorithm based on topological properties of simple smooth surfaces is provided to solve the problem of global reconstruction. Classifying singular points in the shading image as maxima, minima, and two kinds of saddle points serves as the key to the solution of the problem. The global reconstruction procedure, being deterministic and using topological properties of the surface, performs better than other approaches proposed so far that are based on classification of singular points according to the behavior of characteristics in their neighborhood. The proposed algorithm is simple and easy to implement and lends itself to a parallel implementation.