To ensure good performance, modern machine learning models typically require large
amounts of quality annotated data. Meanwhile, the data collection and annotation processes …

Lidars and cameras are critical sensors that provide complementary information for 3D
detection in autonomous driving. While prevalent multi-modal methods simply decorate raw …

Abstract 3D object detection in point clouds is a core component for modern robotics and
autonomous driving systems. A key challenge in 3D object detection comes from the …

Query-based transformer has shown great potential in constructing long-range attention in
many image-domain tasks, but has rarely been considered in LiDAR-based 3D object …

Deep learning (DL) has become one of the mainstream and effective methods for point
cloud analysis tasks such as detection, segmentation and classification. To reduce …

The detection of 3D objects from LiDAR data is a critical component in most autonomous
driving systems. Safe, high speed driving needs larger detection ranges, which are enabled …

There have been two streams in the 3D detection from point clouds: single-stage methods
and two-stage methods. While the former is more computationally efficient, the latter usually …

Synthetic datasets play a critical role in pre-training CNN models for optical flow, but they are
painstaking to generate and hard to adapt to new applications. To automate the process, we …

Recent voxel-based 3D object detectors for autonomous vehicles learn point cloud
representations either from bird eye view (BEV) or range view (RV, aka the perspective …

High-efficiency point cloud 3D object detection operated on embedded systems is important
for many robotics applications including autonomous driving. Most previous works try to …