Abstract: Deep learning approaches have demonstrated high effectiveness in 3D object detection tasks. However, they often suffer from a notable drop in performance on the previously trained classes ...

Tracking 3D objects accurately and consistently is crucial for autonomous vehicles, enabling more reliable downstream tasks such as trajectory prediction and motion planning. Based on the substantial ...

Abstract: Heavily relying on 3D annotations limits the real-world application of 3D object detection. In this letter, we propose a method that does not demand any 3D annotation, while being able to ...

Variants: Each model includes all high-resolution variants, resulting in a total of 1,659,097 3D instances. Specialized Subsets: For the rigged and animated categories of models, we further obtain the ...