Add to Favourites
To login click here
This article discusses the development of 6D pose estimation methods, which are used for 3D object detection and 6D pose estimation. We propose a loss function, a portable module, and a 6D pose estimation model, MagicCubePose, which has good expansion performance and can build more efficient models for different calculation power and scenarios. Experiments show that our model has good real-time detection performance and the highest ADD(-S) accuracy.
