Shape from Shading Using Probability Functions and Belief Propagation

  title={Shape from Shading Using Probability Functions and Belief Propagation},
  author={Jochen Wilhelmy and J{\"o}rg Kr{\"u}ger},
  journal={International Journal of Computer Vision},
Shape-from-shading (SFS) aims to reconstruct the three-dimensional shape of an object from a single shaded image. This article proposes an improved framework based on belief propagation for computing SFS. The implementation of the well-known brightness, integrability and smoothness constraints inside this framework is shown. We implement the constraints as probability density functions. For example, the brightness constraint is a two-dimensional probability density function that relates all… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 32 references

Similar Papers

Loading similar papers…