Reconstruction of high resolution 3D visual information

Given a set of low resolution camera images, it is possible to reconstruct high resolution luminance and depth information, specially if the relative displacements of the image frames are known. We have proposed iterative algorithms for recovering high resolution albedo and depth maps that require no a priori knowledge of the scene, and therefore do not depend on other methods, as regards boundary and initial conditions. The problem of surface reconstruction has been formulated as one of Expectation Maximization (EM) and has been tackled in a probabilistic framework using Markov Random Fields (MRF) [1][3]. As for the depth map, our method is directly recovering surface heights without referring to surface orientations, while increasing the resolution by camera jittering [2]. Conventional statistical models have been coupled with geometrical techniques to construct a general model of the world and the imaging process.