Densely annotating LiDAR point clouds is costly, which often restrains the scalability of fully-
supervised learning methods. In this work, we study the underexplored semi-supervised …

Efficient data utilization is crucial for advancing 3D scene understanding in autonomous
driving, where reliance on heavily human-annotated LiDAR point clouds challenges fully …

Abstract 3D point-clouds and 2D images are different visual representations of the physical
world. While human vision can understand both representations, computer vision models …

Recently, 3D object detection with sparse annotations has received great attention.
However, current detectors usually perform poorly under very limited annotations. To …

Semi-supervised object detection is crucial for 3D scene understanding, efficiently
addressing the limitation of acquiring large-scale 3D bounding box annotations. Existing …

Abstract State-of-the-art 3D object detectors are usually trained on large-scale datasets with
high-quality 3D annotations. However, such 3D annotations are often expensive and time …

In this paper, we present a simple yet effective semi-supervised 3D object detector named
DDS3D. Our main contributions have two-fold. On the one hand, different from previous …

Self-training is a well-established technique in semi-supervised learning, which leverages
unlabeled data by generating pseudo-labels and incorporating them with a limited labeled …

This work proposes the first online asymmetric semi-supervised framework namely A-
Teacher for LiDAR-based 3D object detection. Our motivation stems from the observation …

Current point-cloud detection methods have difficulty detecting the open-vocabulary objects
in the real world, due to their limited generalization capability. Moreover, it is extremely …