Given a set of 2D images, we propose a novel approach for the
reconstruction of straight 3D line segments that represent the
underlying geometry of static 3D objects in the scene. Such an algorithm
is especially useful for the automatic 3D reconstruction of man-made
environments. The main contribution of our approach is the generation of
an improved reconstruction by imposing global topological constraints
given by connections between neighbouring lines. Additionally, our
approach does not employ explicit line matching between views, thus
making it more robust against image noise and partial occlusion.
Furthermore, we suggest a technique to merge independent
reconstructions, that are generated from different base images, which
also helps to remove outliers. The proposed algorithm is evaluated on
synthetic and real scenes by comparison with ground truth.