Bayesian Point Cloud Reconstruction

on Bayesian statistics: The measurement process as well as prior assumptions
on the measured objects are modeled as probability distributions and Bayes~R
rule is used to infer a reconstruction of maximum probability. The key idea
is to define both measurements and reconstructions as point clouds and
describe all statistical assumptions in terms of this finite dimensional
representation. This yields a discretization of the problem that can be
solved using numerical optimization techniques. The resulting algorithm
reconstructs both topology and geometry in form of a well-sampled point
cloud with noise removed. In a final step, this representation is then
converted into a triangle mesh. The proposed framework will be applied to
the reconstruction of objects consisting of piecewise smooth surfaces with
sharp edges. The talk will also show some experimental results and discuss
future extensions of the proposed technique.