Learning Part Boundaries from 3D Point Clouds

TL;DR

This paper introduces a graph convolutional network-based method for detecting part boundaries in 3D point clouds, improving accuracy over existing techniques and aiding in semantic shape segmentation.

Contribution

A novel boundary detection approach using graph convolutional networks that generalizes to semantic and geometric boundaries in 3D shapes.

Findings

More accurate boundary detection compared to alternatives

Effective in semantic shape segmentation tasks

Improves part labeling performance

Abstract

We present a method that detects boundaries of parts in 3D shapes represented as point clouds. Our method is based on a graph convolutional network architecture that outputs a probability for a point to lie in an area that separates two or more parts in a 3D shape. Our boundary detector is quite generic: it can be trained to localize boundaries of semantic parts or geometric primitives commonly used in 3D modeling. Our experiments demonstrate that our method can extract more accurate boundaries that are closer to ground-truth ones compared to alternatives. We also demonstrate an application of our network to fine-grained semantic shape segmentation, where we also show improvements in terms of part labeling performance.