2021/01/07 by Jingyu Gong, Gong, Jingyu, Jiachen Xu +11 · 4 citations
Computer Science · Earth and Planetary Sciences · Engineering · Mathematics · #3D Shape Modeling and Analysis #3D Surveying and Cultural Heritage #Aggregate (composite) #Artificial intelligence #Artificial neural network #Boundary (topology) #Chain code #Code (set theory) #Computer Graphics and Visualization Techniques #Computer science #Computer vision #Convolution (computer science) #ENCODE #Encoding (memory) #Feature (linguistics) #Feature extraction #Geometry #Image (mathematics) #Mathematics #Pattern recognition (psychology) #Point (geometry) #Point cloud #Segmentation #cs.CV
paper · pdf · doi:10.48550/arxiv.2101.02381
published in arXiv (Cornell University) (Cornell University) · Accepted by AAAI2021
arxiv created 2021/01/07 · openalex publication_date 2021/01/07 · arxiv updated 2021/01/08 · openalex created_date 2021/01/18 · openalex updated_date 2026/07/28
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.