Variational relational point completion network for robust 3D classification

• Main Authors: Pan, Liang, Chen, Xinyi, Cai, Zhongang, Zhang, Junzhe, Zhao, Haiyu, Yi, Shuai, Liu, Ziwei
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2023
• Subjects: Engineering::Computer science and engineering; 3D Perception; Point Cloud Completion
• Online Access: https://hdl.handle.net/10356/172185
• Institution: Nanyang Technological University

Real-scanned point clouds are often incomplete due to viewpoint, occlusion, and noise, which hampers 3D geometric modeling and perception. Existing point cloud completion methods tend to generate global shape skeletons and hence lack fine local details. Furthermore, they mostly learn a deterministic...