基于注意力增强的跨模态多层融合网络的物体位姿估计
Object pose estimation based on attention enhancement cross-modal multilayer fusion network
基于注意力增强的跨模态多层融合网络的物体位姿估计 |
| 杨恒,王韶涵,董青,赵科渊,杨明亮 |
|
Object pose estimation based on attention enhancement cross-modal multilayer fusion network |
| Heng YANG,Shaohan WANG,Qing DONG,Keyuan ZHAO,Mingliang YANG |
| 图 5 PoseCNN和地面真实分割的‘large_clamp’ 和‘extra_large_clamp’的ADD(-S)分数-阈值曲线 |
| Fig.5 ADD(-S) score-threshold curve for 'large_clamp' and 'extra_large_clamp' split by PoseCNN and Ground Truth |
|
|