Robustly Extracting Concise 3D Curve Skeletons by Enhancing the Capture of Prominent Features

Extracting concise 3D curve skeletons with existing methods is still a serious challenge as these methods require tedious parameter adjustment to suppress the influence of shape boundary perturbations to avoid spurious branches. In this paper, we address this challenge by enhancing the capture of prominent features and using them for skeleton extraction, motivated by the observation that the shape is mainly represented by prominent features. Our method takes the medial mesh of the shape as input, which can maintain the shape topology well. We develop a series of novel measures for simplifying and contracting the medial mesh to capture prominent features and represent them concisely, by which means the influences of shape boundary perturbations on skeleton extraction are suppressed and the quantity of data needed for skeleton extraction is significantly reduced. As a result, we can robustly and concisely extract the curve skeleton based on prominent features, avoiding the trouble of tuning parameters and saving computations, as shown by experimental results.

Automated summary

This paper addresses the challenge of extracting concise 3D curve skeletons using existing methods. It proposes a method that enhances the capture of prominent features and uses them for skeleton extraction, reducing the influence of shape boundary perturbations and the amount of data needed for extraction. Experimental results show that the proposed method avoids parameter tuning and saves computations.