Causal Scene Deconfounding for 6-DoF Grasp Detection
Robotic grasp detection aims to learn reliable grasp poses from 3D point clouds. Existing methods primarily train neural networks to estimate grasp poses but often overlook the dataset biases stemming from imbalanced scene distributions. Specifically, due to the underrepresentation of densely cluttered and severely occ...
Yang-Fu Zhu, Wei-Zhen Tian, Yuan-Dong Wang et al.
· 0 citations