Abstract: An embodiment of the invention includes a method for identifying a point representing a feature in a 3D dataset. The method includes performing a pick, which includes filtering the dataset to extract a subset of points based on certain criteria including a seed point and evaluating a metric for each point in the subset of points. The metric is a non-normalized probability that the point being evaluated represents the feature. The point or points with the highest metric is identified as representing the feature. Another embodiment of the invention includes a computer-readable medium comprising computer-executable instructions for identifying a point representing a feature in a 3D dataset. Another embodiment of the invention includes a method for displaying a view of a feature in a 3D dataset.