Abstract: 6D pose estimation is a crucial subfield of visual measurement, extensively applied in robotics, autonomous driving, and augmented reality. Existing instance-level and category-level 6D pose ...

Abstract: Category-level 6D pose estimation, predicting the 3D position, orientation, and size of unseen objects, is pivotal for applications in robotics and augmented reality. Existing methodologies ...

The methodology extends traditional CIB analysis with ways to handle uncertainty, test how robust scenarios are, simulate how systems change over time, and model probabilities. The simplest approach ...

We present FoundationPose, a unified foundation model for 6D object pose estimation and tracking, supporting both model-based and model-free setups. Our approach can be instantly applied at test-time ...