Volumetric Tracking by Detection

In this project, instead of hollowed empty surfaces, we parameterize 3D shapes as solid volumes using centroidal Voronoi tessellation (CVT) and in turn realize discriminative correspondences in a volumetric manner. We further propose a unified volumetric tracking-by-detection pipeline, where the shape representation, deformation model, feature description, and primitive association are all built on a single consistent representation, CVT.

1. C. H. Huang, B. Allain, E. Boyer, J.-S. Franco, F. Tombari, N. Navab, and S. Ilic, “Tracking-by-Detection of 3D Human Shapes: from Surfaces to Volumes,” TPAMI, 2017. (pdf, video)

2. C. H. Huang, B. Allain, J.-S. Franco, N. Navab, S. Ilic, and E. Boyer, “Volumetric 3D Tracking by Detection,” CVPR, 2016 (spotlight oral, equal contribution with the second author). (pdf, video, results)

#randomforest