A lot of applications in computer vision are based on a pixel-labelling problem, such as stereomatching, image restoration or object segmentation. In the last years great advances have beenachieved in dense disparity estimation, being Graph Cuts and Belief Propagation two of themost outstanding algorithms. Particularly, Belief Propagation has some characteristics whichmake it very interesting to deal with, i.e. powerful message passing and high flexibility.Furthermore, working with omnidirectional cameras, instead of standard cameras, a smallernumber of images would be needed because of their wider field of view and it would allowreconstructing the 3D scene in an easier way.This project aims to adapt the Belief Propagation algorithm to spherical stereo images. Inaddition, as working with spherical images, we should take into account that these images willbe projected on a sphere, being then the pixels at different distances between them. Thus, theproject also aims to improve the algorithm adding a weighting function which considers thedistance between the points on the sphere.The project contains the general description of the proposed framework as well as an analysis and evaluation of the results obtained after its implementation.