2022
OVE6D: Object Viewpoint Encoding for Depth-Based 6D Object Pose Estimation
CVPR 2022poster
This paper proposes a universal framework, called OVE6D, for model-based 6D object pose estimation from a single depth image and a target object mask. Our model is trained using purely synthetic data rendered from ShapeNet, and, unlike most of the existing methods, it generalizes well on new real-wo…