Implementations of some of the algorithms we have developed are available for download. If you find these to be useful for your research publications, please cite the article or articles mentioned on the corresponding pages.

  • Code for computing skeletons using our notion of average outward flux is available on this github page.
  • Code for dominant set clustering and pooling for multi-view 3D object recognition is available on this github page.
  • Code for local spectral graph convolution for point set feature learning is available on this github page.
  • Databases

    The McGill 3D Shape Benchmark offers a repository for testing 3D shape retrieval algorithms. The emphasis is on including models with articulating parts. Thus, whereas some models have been adapted from the the Princeton Shape Benchmark and others have been downloaded from different web repositories, a substantial number have been created by us using CAD modeling tools. We provide the models in both "voxelized" form (using the .im file format, corresponding to the KUIM package) as well as in "mesh" form (using the .ply format). In the voxelized format voxels within the interior of an object have a different label than those in the background. In the mesh format each object's surface is provided in triangulated form. The mesh representations correspond to the boundary voxels of the corresponding voxel representations. They are therefore are "jagged" and may need to be smoothed for some applications. The models are organized in two databases. The first contains objects with articulating parts and the second objects whose parst undergo minor or no articulation. Within each database there are a number of ``basic'' level categories and in each there are typically between 20 to 30 examplars. Dr. Alexander Agathos has kindly contributed manifold mesh versions of these models in .off format. These are also available for download. If you use this database in your research publications we request that you reference the associated paper: K.Siddiqi, J. Zhang, D. Macrini, A. Shokoufandeh, S. Bouix and S. Dickinson. Retrieving Articulated 3D Models Using Medial Surfaces. Machine Vision and Applications, 19(4), 261--274, 2008.