Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds

01/07/2021
by   Jingyu Gong, et al.
0

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.

READ FULL TEXT

page 2

page 4

page 6

research
01/28/2022

Neighborhood-aware Geometric Encoding Network for Point Cloud Registration

The distinguishing geometric features determine the success of point clo...
research
01/24/2020

SceneEncoder: Scene-Aware Semantic Segmentation of Point Clouds with A Learnable Scene Descriptor

Besides local features, global information plays an essential role in se...
research
03/29/2021

Enhanced Boundary Learning for Glass-like Object Segmentation

Glass-like objects such as windows, bottles, and mirrors exist widely in...
research
07/18/2023

MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds

3D semantic segmentation on multi-scan large-scale point clouds plays an...
research
04/27/2023

Automatically Segment the Left Atrium and Scars from LGE-MRIs Using a Boundary-focused nnU-Net

Atrial fibrillation (AF) is the most common cardiac arrhythmia. Accurate...
research
05/26/2022

SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation

Conventional point cloud semantic segmentation methods usually employ an...
research
12/23/2022

Push-the-Boundary: Boundary-aware Feature Propagation for Semantic Segmentation of 3D Point Clouds

Feedforward fully convolutional neural networks currently dominate in se...

Please sign up or login with your details

Forgot password? Click here to reset