Three-Dimensional Group Registration of Mesh Objects
In this work we propose a fully automatic and computationally efficient approach for the group registration of sets of three-dimensional models represented as mesh objects. Our approach is based on agglomerating the set of pairwise model-to-model rigid registrations by a robust spectral synchronization scheme. The pairwise registration is computed using spectral graph matching applied to meshes via the LD-SIFT local mesh features. We applied the proposed scheme to sets of medical models, and it was shown to provide accurate and robust registration results.
* Research was carried out towards the M.Sc. degree in Electrical Engineering, advised by Dr. Yosi Keller, Faculty of Engineering, Bar-Ilan University