We propose a new way of embedding shape distributions in a topological deformable template. These distributions rely on global shape descriptors corresponding to the 3D moment inva...
Non-rigid structure from motion (NRSFM) is a difficult, underconstrained problem in computer vision. The standard approach in NRSFM constrains 3D shape deformation using a linear...
In this paper, we address the tasks of detecting, segmenting, parsing, and matching deformable objects. We use a novel probabilistic object model that we call a hierarchical defor...
The paper presents a new parameter-free approach to non-rigid image registration, where displacements, obtained through a mapping of boundary structures in the source and target i...
This article proposes a hyperelastic 3D deformable template for the segmentation of soft structures. It relies on a template, which is a topological, geometrical and material model...