Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds

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 boundaryaware 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 boundaryaware 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.

Authors

• Jingyu Gong East China Normal University
• Jiachen Xu
• Xin Tan East China Normal University, Shanghai, China
• Jie Zhou East China Normal University
• Yanyun Qu School of Informatics, Xiamen University Institute of Artificial Intelligence, Xiamen University Key Laboratory of Multimedia Trusted Perception and Efficient Computing,Ministry of Education of China, Xiamen University
• Yuan Xie East China Normal University, Shanghai, China
• Lizhuang Ma Shanghai Jiao Tong University, Shanghai, China East China Normal University, Shanghai, China MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China

Keywords

No keywords are indexed for this paper.