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

• المؤلفون الرئيسيون: Liu, Tianrui, Cai, Yiyu, Zheng, Jianmin, Thalmann, Nadia Magnenat
• مؤلفون آخرون: Interdisciplinary Graduate School (IGS)
• التنسيق: مقال
• اللغة: English
• منشور في: 2021
• الموضوعات: Engineering; 3D Point Cloud; Instance Segmentation
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/148247

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...