In this work, we tackle the limitations of current LiDAR-based 3D object detection systems,
which are hindered by a restricted class vocabulary and the high costs associated with …

This paper proposes an algorithm for automatically labeling 3D objects from 2D point or box
prompts, especially focusing on applications in autonomous driving. Unlike previous arts …

Abstract 3D object detection is an indispensable component for scene understanding.
However, the annotation of large-scale 3D datasets requires significant human effort. To …

Instance segmentation is a fundamental research in computer vision, especially in
autonomous driving. However, manual mask annotation for instance segmentation is quite …

Accurate object detection in LiDAR point clouds is a key prerequisite of robust and safe
autonomous driving and robotics applications. Training the 3D object detectors currently …

Weakly supervised 3D object detection aims to learn a 3D detector with lower annotation
cost, eg, 2D labels. Unlike prior work which still relies on few accurate 3D annotations, we …

Abstract 3D automatic annotation has received increased attention since manually
annotating 3D point clouds is laborious. However, existing methods are usually complicated …

LiDAR-based outdoor 3D object detection has received widespread attention. However,
training 3D detectors from the LiDAR point cloud typically relies on expensive bounding box …

Advancements in deep learning-based 3D object detection necessitate the availability of
large-scale datasets. However, this requirement introduces the challenge of manual …

3D object detection plays a crucial role in various applications such as autonomous
vehicles, robotics and augmented reality. However, training 3D detectors requires a costly …