Abstract:
This paper presents a framework for implicit deformable
models and a pair of new algorithms for solving the
nonlinear partial differential equations
that result from this framework.
Implicit models offer a useful alternative to parametric models,
particularly when dealing with the deformation of higher-dimensional
objects.
The basic expressions for the evolution of implicit models are relatively
straightforward; they follow as a direct consequence of the chain rule for
differentiation.
More challenging, however, is the development of algorithms that are
stable and efficient.
The first algorithm is a viscosity approximation which gives solutions over a dense set in the range, providing a means of calculating the solutions of embedded families of contours simultaneously. The second algorithm incorporates sparse solutions for a discrete set of contours. This sparse-field method requires a fraction of the computation compared to the first but offers solutions only for a finite number of contours. Results from 3d medical data as well as video images are shown.