Point2Skeleton: Learning Skeletal Representations from Point Clouds
This method provides a more robust and generalized skeletonization technique for point clouds, which could benefit downstream unsupervised tasks like surface reconstruction and segmentation for researchers working with 3D data.
This paper introduces Point2Skeleton, an unsupervised method that learns skeletal representations directly from point clouds. It addresses limitations of existing methods by handling complex structures and non-watertight inputs, producing generalized skeletal representations.
We introduce Point2Skeleton, an unsupervised method to learn skeletal representations from point clouds. Existing skeletonization methods are limited to tubular shapes and the stringent requirement of watertight input, while our method aims to produce more generalized skeletal representations for complex structures and handle point clouds. Our key idea is to use the insights of the medial axis transform (MAT) to capture the intrinsic geometric and topological natures of the original input points. We first predict a set of skeletal points by learning a geometric transformation, and then analyze the connectivity of the skeletal points to form skeletal mesh structures. Extensive evaluations and comparisons show our method has superior performance and robustness. The learned skeletal representation will benefit several unsupervised tasks for point clouds, such as surface reconstruction and segmentation.