Oliver Burghard

Learn More
We introduce morphable part models for smart shape manipulation using an assembly of deformable parts with appropriate boundary conditions. In an analysis phase, we characterize the continuous allowable variations both for the individual parts and their interconnections using Gaussian shape models with low rank covariance. The discrete aspect of how parts(More)
We consider the problem of establishing dense correspondences within a set of related shapes of strongly varying geometry. For such input, traditional shape matching approaches often produce unsatisfactory results. We propose an ensemble optimization method that improves given coarse correspondences to obtain dense correspondences. Following ideas from(More)
Figure 1: With this benchmark we evaluate the accuracy of matching algorithms when presented with 3D deformable shapes undergoing topological changes. Shown in the figure is a subset of shapes from the proposed dataset. The red marks indicate parts of the shape where a topological " shortcut " takes place: there, the triangular mesh is modified so as to(More)
  • 1