Autonomous driving, in recent years, has been receiving increasing attention for its potential
to relieve drivers' burdens and improve the safety of driving. In modern autonomous driving …

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 …

We present a simple yet effective fully convolutional one-stage 3D object detector for LiDAR
point clouds of autonomous driving scenes, termed FCOS-LiDAR. Unlike the dominant …

In order to deal with the sparse and unstructured raw point clouds, most LiDAR based 3D
object detection research focuses on designing dedicated local point aggregators for fine …

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 …

This paper tries to address a fundamental question in point cloud self-supervised learning:
what is a good signal we should leverage to learn features from point clouds without …

It is a long-term vision for Autonomous Driving (AD) community that the perception models
can learn from a large-scale point cloud dataset, to obtain unified representations that can …

Extending the success of 2D Large Kernel to 3D perception is challenging due to: 1. the
cubically-increasing overhead in processing 3D data; 2. the optimization difficulties from …

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

Recent advance in 2D CNNs has revealed that large kernels are important. However, when
directly applying large convolutional kernels in 3D CNNs, severe difficulties are met, where …