Existing point-cloud based 3D object detectors use convolution-like operators to process
information in a local neighbourhood with fixed-weight kernels and aggregate global context …

In this paper, we address the 3D object detection task by capturing multi-level contextual
information with the self-attention mechanism and multi-scale feature fusion. Most existing …

We present a novel and high-performance 3D object detection framework, named
PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds. Our …

We present a flexible and high-performance framework, named Pyramid R-CNN, for two-
stage 3D object detection from point clouds. Current approaches generally rely on the points …

Real-time and high-performance 3D object detection is of critical importance for autonomous
driving. Recent top-performing 3D object detectors mainly rely on point-based or 3D voxel …

The most recent 3D object detectors for point clouds rely on the coarse voxel-based
representation rather than the accurate point-based representation due to a higher box …

Point-cloud based 3D object detectors recently have achieved remarkable progress.
However, most studies are limited to the development of network architectures for improving …

In this paper, we aim at addressing two critical issues in the 3D detection task, including the
exploitation of multiple sensors (namely LiDAR point cloud and camera image), as well as …

We address the problem of 3D object detection, that is, estimating 3D object bounding boxes
from point clouds. 3D object detection methods exploit either voxel-based or point-based …

Current 3D object detection paradigms highly rely on extensive annotation efforts, which
makes them not practical in many real-world industrial applications. Inspired by that a …