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 …

The recognition capabilities of current state-of-the-art 3D models are limited by datasets with
a small number of annotated data and a pre-defined set of categories. In its 2D counterpart …

LiDAR and camera are two important sensors for 3D object detection in autonomous driving.
Despite the increasing popularity of sensor fusion in this field, the robustness against inferior …

Abstract 3D point cloud segmentation has made tremendous progress in recent years. Most
current methods focus on aggregating local features, but fail to directly model long-range …

Recent advancements in multimodal pre-training have shown promising efficacy in 3D
representation learning by aligning multimodal features across 3D shapes their 2D …

Modern 3D semantic instance segmentation approaches predominantly rely on specialized
voting mechanisms followed by carefully designed geometric clustering techniques. Building …

One-to-one set matching is a key design for DETR to establish its end-to-end capability, so
that object detection does not require a hand-crafted NMS (non-maximum suppression) to …

We propose octree-based transformers, named OctFormer, for 3D point cloud learning.
OctFormer can not only serve as a general and effective backbone for 3D point cloud …

Designing an efficient yet deployment-friendly 3D backbone to handle sparse point clouds is
a fundamental problem in 3D perception. Compared with the customized sparse …