This paper presents a method for the generation of landmarks in three-dimensional shapes and the construction of the corresponding 3-D statistical shape models. The technique relies on establishing shape correspondances via a volumetric non-rigid registration technique using multi-resolution B-spline deformations. This approach presents some advantages over previously published methods: it can treat multiple-part structures, and it requires less restrictive assumptions on the structure’s topology. In this paper we address the problem of building a three-dimensional statistical shape model of the left and right ventricles of the heart from 3-D Magnetic Resonance (MR) images. This application demonstrates the robustness and accuracy of the method in the presence of large shape variability and multiple objects.