Abstract
A novel formulation for shape-from-shading from multiple images acquired under different viewing and lighting conditions is presented. The method is based on using an explicit image formation model to create renditions of the surface being estimated, which are synthetic versions of the observed images. It is applicable in a variety of imaging situations, including those involving unknown nonuniform albedo. A probabilistic model is developed based on typical characteristics of the surface and minimizing the difference between the synthetic and observed images. This model is used to arrive at Bayesian formulation of the shape-from-shading problem. Techniques are presented to compute an estimate that is statistically optimal in the sense that it is the expected value of the surface, given the set of observations derived from it. The method is applied to Viking imagery of Mars.

This publication has 11 references indexed in Scilit: