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 …

The 3D point cloud (3DPC) has significantly evolved and benefited from the advance of
deep learning (DL). However, the latter faces various issues, including the lack of data or …

Recent progress in 3D object detection from single images leverages monocular depth
estimation as a way to produce 3D pointclouds, turning cameras into pseudo-lidar sensors …

Current perception models in autonomous driving have become notorious for greatly relying
on a mass of annotated data to cover unseen cases and address the long-tail problem. On …

In autonomous driving, a LiDAR-based object detector should perform reliably at different
geographic locations and under various weather conditions. While recent 3D detection …

Unlike RGB cameras that use visible light bands (384∼ 769 THz) and Lidars that use
infrared bands (361∼ 331 THz), Radars use relatively longer wavelength radio bands (77∼ …

We present a new domain adaptive self-training pipeline, named ST3D, for unsupervised
domain adaptation on 3D object detection from point clouds. First, we pre-train the 3D …

Modern neural networks use building blocks such as convolutions that are equivariant to
arbitrary 2 D translations. However, these vanilla blocks are not equivariant to arbitrary 3 D …

Abstract Domain adaptation is crucial to adapt a learned model to new scenarios, such as
domain shifts or changing data distributions. Current approaches usually require a large …

Reliable and accurate 3D object detection is a necessity for safe autonomous driving.
Although LiDAR sensors can provide accurate 3D point cloud estimates of the environment …