Point2Skeleton: Learning Skeletal Representations from Point Clouds

12/01/2020
by   Cheng Lin, et al.
5

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.

READ FULL TEXT

page 3

page 12

research
01/14/2019

PointWise:An Unsupervised Point-wise Feature Learning Network

The availability and plethora of unlabeled point-clouds as well as their...
research
10/03/2021

Coverage Axis: Inner Point Selection for 3D Shape Skeletonization

In this paper, we present a simple yet effective formulation called Cove...
research
09/29/2022

Exploring Cross-Point Embeddings for 3D Dense Uncertainty Estimation

Dense prediction tasks are common for 3D point clouds, but the inherent ...
research
09/17/2009

Succinct Representation of Well-Spaced Point Clouds

A set of n points in low dimensions takes Theta(n w) bits to store on a ...
research
07/08/2019

Learning Structural Graph Layouts and 3D Shapes for Long Span Bridges 3D Reconstruction

A learning-based 3D reconstruction method for long-span bridges is propo...
research
12/31/2021

Representation Topology Divergence: A Method for Comparing Neural Network Representations

Comparison of data representations is a complex multi-aspect problem tha...
research
10/17/2020

Generating Large Convex Polytopes Directly on Point Clouds

In this paper, we present a method to efficiently generate large, free, ...

Please sign up or login with your details

Forgot password? Click here to reset