BEACon : a boundary embedded attentional convolution network for point cloud instance segmentation

• Main Authors: Liu, Tianrui, Cai, Yiyu, Zheng, Jianmin, Thalmann, Nadia Magnenat
• Other Authors: Interdisciplinary Graduate School (IGS)
• Format: Article
• Language: English
• Published: 2021
• Subjects: Engineering; 3D Point Cloud; Instance Segmentation
• Online Access: https://hdl.handle.net/10356/148247
• Institution: Nanyang Technological University

Motivated by how humans perceive geometry and color to recognize objects, we propose a Boundary Embedded Attentional Convolution (BEACon) network for point cloud instance segmentation. At the core of BEACon, we introduce the attentional weight in the convolution layer to adjust the neighboring featu...