The distillation can also cover 3D object boxes on the background.

A vision model with general-purpose object-level 3D understanding should be capable of inferring both 2D ( e.g., class name and bounding box) and 3D information ( e.g., 3D location and 3D viewpoint) for arbitrary rigid objects in natural

Subsequently, the generated 2D masks are employed to align mask-level 3D representations with the vision-language feature space, thereby augmenting the open vocabulary capability of 3D geometry embeddings.

We refer to it as theContinuous Category Discovery(CCD) problem, which is significantly more challenging than the static setting.

Articulated object manipulation is a fundamental yet challenging task in robotics. Due to significant geometric and semantic variations across object categories, previous manipulation models struggle to generalize to novel categories. Few-shot learning is a promising solution for alleviating this issue by allowing robots to perform a few interactions with unseen objects.