Finite Element Based Tracking of Deforming Surfaces
This work addresses the challenge of robust 3D tracking for deformable objects in computer vision, but it is incremental as it builds on existing finite element and template-based methods.
The paper tackles the problem of tracking the geometry of deforming objects from single-viewpoint point clouds, using a linear finite element method combined with a smooth template to accurately reconstruct both observed and unobserved sides, with results demonstrated on noisy data from stereo or depth cameras and simulations with various error terms.
We present an approach to robustly track the geometry of an object that deforms over time from a set of input point clouds captured from a single viewpoint. The deformations we consider are caused by applying forces to known locations on the object's surface. Our method combines the use of prior information on the geometry of the object modeled by a smooth template and the use of a linear finite element method to predict the deformation. This allows the accurate reconstruction of both the observed and the unobserved sides of the object. We present tracking results for noisy low-quality point clouds acquired by either a stereo camera or a depth camera, and simulations with point clouds corrupted by different error terms. We show that our method is also applicable to large non-linear deformations.