Parameterizing Deformable Surfaces for Monocular 3–D Tracking

We propose a deformable surface parameterization that is generic and lets us automatically build registered shape databases. This allows us to directly derive low-dimensional shape models using a simple dimensionality reduction technique. This addresses one of the biggest difficulties in example-based shape modeling: Building the required database, which is often a difficult and painstaking process. We incorporate the resulting models into a monocular tracking system that we use to capture the complex deformations of objects such as sheets of papers or expanding balloons from single video sequences.