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 …

Learning powerful representations in bird's-eye-view (BEV) for perception tasks is trending
and drawing extensive attention both from industry and academia. Conventional …

Fusing the camera and LiDAR information has become a de-facto standard for 3D object
detection tasks. Current methods rely on point clouds from the LiDAR sensor as queries to …

Non-uniformed 3D sparse data, eg, point clouds or voxels in different spatial positions, make
contribution to the task of 3D object detection in different ways. Existing basic components in …

How should we integrate representations from complementary sensors for autonomous
driving? Geometry-based fusion has shown promise for perception (eg, object detection …

Abstract We present Voxel Transformer (VoTr), a novel and effective voxel-based
Transformer backbone for 3D object detection from point clouds. Conventional 3D …

Transformer has demonstrated promising performance in many 2D vision tasks. However, it
is cumbersome to apply the self-attention underlying transformer on large-scale point cloud …

Abstract We present Self-Ensembling Single-Stage object Detector (SE-SSD) for accurate
and efficient 3D object detection in outdoor point clouds. Our key focus is on exploiting both …

Lidar-based sensing drives current autonomous vehicles. Despite rapid progress, current
Lidar sensors still lag two decades behind traditional color cameras in terms of resolution …

Though 3D object detection from point clouds has achieved rapid progress in recent years,
the lack of flexible and high-performance proposal refinement remains a great hurdle for …