VFL3D: A single-stage fine-grained lightweight point cloud 3D object detection algorithm based on voxels

B Li, J Chen, X Li, R Xu, Q Li, Y Cao… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
In this work, we propose a voxel-based single-stage fine-grained and efficient point cloud
3D object detection algorithm to address the inadequate granularity in point cloud feature …

Boundary points guided 3D object detection for point clouds

Q Tang, M Yang, Z Wang, W Dong, Y Liu - Applied Soft Computing, 2024 - Elsevier
Abstract 3D object detection in LiDAR point clouds is crucial for computer vision tasks such
as autonomous driving. The two-stage approach with point cloud completion achieves …

CAFI-pillars: Infusing geometry priors for pillar-based 3D detectors through centroid-aware feature interaction

C Wang, Z Liu - IEEE Transactions on Intelligent Vehicles, 2023 - ieeexplore.ieee.org
Pillar-based feature learning patterns have demonstrated high efficiency for 3D object
detection, fostering the research of environmental perception for autonomous vehicles …

Joint Representation Learning Based on Feature Center Region Diffusion and Edge Radiation for Cross-view Geo-localization

F Ge, Y Zhang, L Wang, Y Liu, P Si… - … on Geoscience and …, 2024 - ieeexplore.ieee.org
The essence of the cross-view geo-localization task is to accurately identify the same object
across images captured from different viewpoints. Due to variations in image acquisition …

Deformable Shape-Aware Point Generation for 3D Object Detection

K Wang, X Zhang - Proceedings of the Asian Conference on …, 2024 - openaccess.thecvf.com
As a fundamental task of the perception system for au tonomous driving, LiDAR-based 3D
object detection often suffers from the absence of incomplete object shapes under long …

PEPillar: a point-enhanced pillar network for efficient 3D object detection in autonomous driving

L Sun, Y Li, W Qin - The Visual Computer, 2024 - Springer
Pillar-based 3D object detection methods outperform traditional point-based and voxel-
based methods in terms of speed. However, most of recent methods in this category use …

Dense Voxel Representation Network for Implicit Scene Completion

F Dai, Y Zhu, Y Shen, J **e… - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
Implicit scene completion aims to learn an implicit representation of dense point clouds from
incomplete ones. Since point clouds are disordered and irregular, some implicit scene …