Point2Skeleton: Learning Skeletal Representations from Point Clouds
Cheng Lin1Changjian Li2Yuan Liu1,  Nenglun Chen1
Yi-King Choi1Wenping Wang1
1The University of Hong Kong,   2University College London
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
Oral Presentation
Paper teaser
Fig. 1. We introduce an unsupervised method to learn skeletal meshes from point clouds. The skeletal meshes contain both 1D curve segments and 2D surface sheets which can represent underlying structures of various shapes.
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.
  Paper [PDF]

Code [Github]

Lin C, Li C, Liu Y, et al. Point2Skeleton: Learning Skeletal Representations from Point Clouds[J]. arXiv preprint arXiv:2012.00230, 2020.  (bibtex)

Network Overview
Fig. 2. An overview of our Point2Skeleton pipeline. Given a point cloud as input, we first learn a geometric transformation via convex combinations to predict the skeletal points together with their radii. Second, we connect the skeletal points to form mesh structures. We initialize a graph structure using two simple priors derived from the properties of skeletal mesh; and then we formulate a link prediction problem using a graph auto-encoder to obtain a complete skeletal mesh.
Representative Results
Fig. 3. Qualitative comparison with the competitive point cloud skeletonization methods, i.e., L1-medial skeleton and deep point consolidation (DPC)
Applications - Reconstruction
Fig. 4. Unsupervised surface reconstruction from point clouds. Our method can produce watertight surfaces that capture more detail of thin structures without the need of normal vectors.
Applications - Segmentation
Fig. 5. Unsupervised structural decomposition for point clouds using the skeletal meshes generated by our method.
Applications - Inpaiting
Fig. 6. Skeletal mesh prediction for reconstructing complete geometries from point clouds with missing regions.
©Changjian Li. Last update: March 7, 2021.