Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds

TL;DR

This paper introduces a boundary-aware geometric encoding framework for 3D point cloud segmentation, leveraging boundary prediction and geometric convolution to improve feature discrimination and achieve state-of-the-art results.

Contribution

The paper proposes a novel boundary prediction module and a boundary-aware geometric encoding module with a lightweight geometric convolution for enhanced point cloud segmentation.

Findings

Significant improvement over baseline methods.

Achieves state-of-the-art performance on ScanNet v2 and S3DIS.

Boundary-aware encoding effectively reduces misclassification in transition areas.

Abstract

Boundary information plays a significant role in 2D image segmentation, while usually being ignored in 3D point cloud segmentation where ambiguous features might be generated in feature extraction, leading to misclassification in the transition area between two objects. In this paper, firstly, we propose a Boundary Prediction Module (BPM) to predict boundary points. Based on the predicted boundary, a boundary-aware Geometric Encoding Module (GEM) is designed to encode geometric information and aggregate features with discrimination in a neighborhood, so that the local features belonging to different categories will not be polluted by each other. To provide extra geometric information for boundary-aware GEM, we also propose a light-weight Geometric Convolution Operation (GCO), making the extracted features more distinguishing. Built upon the boundary-aware GEM, we build our network and test it on benchmarks like ScanNet v2, S3DIS. Results show our methods can significantly improve the baseline and achieve state-of-the-art performance. Code is available at https://github.com/JchenXu/BoundaryAwareGEM.