Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds
This work provides an incremental improvement in semantic segmentation accuracy for point clouds, which is beneficial for applications like robotics and autonomous driving where precise object delineation is crucial.
This paper addresses the issue of ambiguous features in 3D point cloud segmentation, which often leads to misclassification at object boundaries. The authors propose a Boundary Prediction Module (BPM) and a boundary-aware Geometric Encoding Module (GEM) to improve feature discrimination, achieving state-of-the-art performance on benchmarks like ScanNet v2 and S3DIS.
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.