Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds

Authors

  • Jingyu Gong Shanghai Jiao Tong University
  • Jiachen Xu Shanghai Jiao Tong University
  • Xin Tan Shanghai Jiao Tong University City University of Hong Kong
  • Jie Zhou City University of Hong Kong
  • Yanyun Qu Xiamen University
  • Yuan Xie East China Normal University
  • Lizhuang Ma Shanghai Jiao Tong University East China Normal University

DOI:

https://doi.org/10.1609/aaai.v35i2.16232

Keywords:

3D Computer Vision, Scene Analysis & Understanding, Segmentation

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.
AAAI-21 Proceedings Cover

Downloads

Published

2021-05-18

How to Cite

Gong, J., Xu, J., Tan, X., Zhou, J., Qu, Y., Xie, Y., & Ma, L. (2021). Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds. Proceedings of the AAAI Conference on Artificial Intelligence, 35(2), 1424-1432. https://doi.org/10.1609/aaai.v35i2.16232

Issue

Vol. 35 No. 2: AAAI-21 Technical Tracks 2

Section

AAAI Technical Track on Computer Vision I