Pyramid U-Network for Skeleton Extraction From Shape Points

Code

• github.com/roatienza/skelnet
  In papernone★ 0

Abstract

The knowledge about the skeleton of a given geometric shape has many practical applications such as shape animation, shape comparison, shape recognition, and estimating structural strength. Skeleton extraction becomes a more challenging problem when the topology is represented in point cloud domain. In this paper, we present the network architecture, PSPU-SkelNet, for TeamPH which ranked 3rd in Point SkelNetOn 2019 challenge. PSPU-SkelNet is a pyramid of three U-Nets that predicts the skeleton from a given shape point cloud. PSPU-SkelNet achieves a Chamfer Distance (CD) of 2.9105 on the final test dataset. The code of PSPU SkelNet is available at https://github.com/roatienza/skelnet.

Reproductions