Efficient Topology-Controlled Sampling of Implicit Shapes
This work addresses computational efficiency in shape sampling for image segmentation, but it is incremental as it builds directly on prior methods.
The paper tackles the problem of sampling from distributions of implicitly defined shapes for image segmentation by extending a Metropolis-Hastings method to accept samples at every iteration, achieving an order of magnitude speed-up in convergence, and incorporating topological constraints.
Sampling from distributions of implicitly defined shapes enables analysis of various energy functionals used for image segmentation. Recent work describes a computationally efficient Metropolis-Hastings method for accomplishing this task. Here, we extend that framework so that samples are accepted at every iteration of the sampler, achieving an order of magnitude speed up in convergence. Additionally, we show how to incorporate topological constraints.