LiDAR-based 3D object detection, semantic segmentation, and panoptic segmentation are
usually implemented in specialized networks with distinctive architectures that are difficult to …

In recent years, electric vehicles have achieved rapid development. Intelligence is one of the
important trends to promote the development of electric vehicles. As a result, autonomous …

Abstract 3D point-clouds and 2D images are different visual representations of the physical
world. While human vision can understand both representations, computer vision models …

While numerous 3D detection works leverage the complementary relationship between RGB
images and point clouds, developments in the broader framework of semi-supervised object …

3D visual recognition is a prerequisite for most autonomous robotic systems operating in the
real world. It empowers robots to perform a variety of tasks, such as tracking, understanding …

Multi-modality fusion and multi-task learning are becoming trendy in 3D autonomous driving
scenario, considering robust prediction and computation budget. However, naively …

Recently, the pure camera-based Bird's-Eye-View (BEV) perception provides a feasible
solution for economical autonomous driving. However, the existing BEV-based multi-view …

3D perception on point-cloud is a challenging and crucial computer vision task. A point-
cloud consists of a sparse, unstructured, and unordered set of points. To understand a point …

This technical report presents the 1st place winning solution for the Waymo Open Dataset
3D semantic segmentation challenge 2022. Our network, termed LidarMultiNet, unifies the …

Restoring an accurate Bird's Eye View (BEV) map plays a crucial role in the perception of
autonomous driving. The existing works of lifting representations from frontal view to BEV …