Abstract 3D point clouds are a crucial type of data collected by LiDAR sensors and widely
used in transportation applications due to its concise descriptions and accurate localization …

In recent years, deep learning techniques for processing 3D point cloud data have seen
significant advancements, given their unique ability to extract relevant features and handle …

Instance contrast for unsupervised representation learning has achieved great success in
recent years. In this work, we explore the idea of instance contrastive learning in …

In a point cloud sequence, 3D object tracking aims to predict the location and orientation of
an object in the current search point cloud given a template point cloud. Motivated by the …

Recent advancements in vision foundation models (VFMs) have opened up new
possibilities for versatile and efficient visual perception. In this work, we introduce Seal, a …

3D segmentation is a fundamental and challenging problem in computer vision with
applications in autonomous driving and robotics. It has received significant attention from the …

Learning effective representations from unlabeled data is a challenging task for point cloud
understanding. As the human visual system can map concepts learned from 2D images to …

In recent years, 3D representation learning has turned to 2D vision-language pre-trained
models to overcome data scarcity challenges. However, existing methods simply transfer 2D …

In the past decade, deep neural networks have achieved significant progress in point cloud
learning. However, collecting large-scale precisely-annotated point clouds is extremely …

Autonomous driving perception has made significant strides in recent years, but accurately
sensing the environment using a single sensor remains a daunting task. This review offers a …