Autonomous vehicles require constant environmental perception to obtain the distribution of
obstacles to achieve safe driving. Specifically, 3D object detection is a vital functional …

In the realm of modern autonomous driving, the perception system is indispensable for
accurately assessing the state of the surrounding environment, thereby enabling informed …

Abstract 3D object detectors usually rely on hand-crafted proxies, eg, anchors or centers,
and translate well-studied 2D frameworks to 3D. Thus, sparse voxel features need to be …

Abstract Recently, virtual/pseudo-point-based 3D object detection that seamlessly fuses
RGB images and LiDAR data by depth completion has gained great attention. However …

LiDAR-camera fusion methods have shown impressive performance in 3D object detection.
Recent advanced multi-modal methods mainly perform global fusion, where image features …

In the context of autonomous driving the significance of effective feature learning is widely
acknowledged. While conventional 3D self-supervised pre-training methods have shown …

Despite the tremendous progress of Masked Autoencoders (MAE) in developing vision tasks
such as image and video, exploring MAE in large-scale 3D point clouds remains …

A key challenge for LiDAR-based 3D object detection is to capture sufficient features from
large scale 3D scenes especially for distant or/and occluded objects. Albeit recent efforts …

LiDAR and cameras are complementary sensors for 3D object detection in autonomous
driving. However, it is challenging to explore the unnatural interaction between point clouds …

Recent Transformer-based 3D object detectors learn point cloud features either from point-
or voxel-based representations. However, the former requires time-consuming sampling …