Abstract 3D object detectors usually rely on hand-crafted proxies, eg, anchors or centers, and translate well-studied 2D frameworks to 3D. Thus, sparse voxel features need to be …
Z Tian, X Chu, X Wang, X Wei… - Advances in Neural …, 2022 - proceedings.neurips.cc
We present a simple yet effective fully convolutional one-stage 3D object detector for LiDAR point clouds of autonomous driving scenes, termed FCOS-LiDAR. Unlike the dominant …
J Li, C Luo, X Yang - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
In order to deal with the sparse and unstructured raw point clouds, most LiDAR based 3D object detection research focuses on designing dedicated local point aggregators for fine …
H Yang, T He, J Liu, H Chen, B Wu… - Proceedings of the …, 2023 - openaccess.thecvf.com
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 …
X Tian, H Ran, Y Wang, H Zhao - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
This paper tries to address a fundamental question in point cloud self-supervised learning: what is a good signal we should leverage to learn features from point clouds without …
It is a long-term vision for Autonomous Driving (AD) community that the perception models can learn from a large-scale point cloud dataset, to obtain unified representations that can …
T Lu, X Ding, H Liu, G Wu… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Extending the success of 2D Large Kernel to 3D perception is challenging due to: 1. the cubically-increasing overhead in processing 3D data; 2. the optimization difficulties from …
Recent Transformer-based 3D object detectors learn point cloud features either from point- or voxel-based representations. However, the former requires time-consuming sampling …
Recent advance in 2D CNNs has revealed that large kernels are important. However, when directly applying large convolutional kernels in 3D CNNs, severe difficulties are met, where …