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

In the realm of modern autonomous driving, the perception system is indispensable for
accurately assessing the state of the surrounding environment, thereby enabling informed …

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 …

Abstract 3D object detection is receiving increasing attention from both industry and
academia thanks to its wide applications in various fields. In this paper, we propose Point …

Jointly processing information from multiple sensors is crucial to achieving accurate and
robust perception for reliable autonomous driving systems. However, current 3D perception …

We present a novel two-stage fully sparse convolutional 3D object detection framework,
named CAGroup3D. Our proposed method first generates some high-quality 3D proposals …

Despite the tremendous progress of Masked Autoencoders (MAE) in developing vision tasks
such as image and video, exploring MAE in large-scale 3D point clouds remains …

This paper presents the first significant object detection framework, NeRF-RPN, which
directly operates on NeRF. Given a pre-trained NeRF model, NeRF-RPN aims to detect all …

Recently, transformer-based methods have dominated 3D instance segmentation, where
mask attention is commonly involved. Specifically, object queries are guided by the initial …

Existing point cloud based 3D detectors are designed for the particular scene, either indoor
or outdoor ones. Because of the substantial differences in object distribution and point …