activity
20202022
most citedTransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers

28 citations · 48 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2022★ 3 cited

LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation

Zeyu Hu, Xuyang Bai, Runze Zhang +4

We propose LiDAL, a novel active learning method for 3D LiDAR semantic segmentation by exploiting inter-frame uncertainty among LiDAR frames. Our core idea is that a well-trained m…

cs.CV2022★ 28 cited

TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers

Xuyang Bai, Zeyu Hu, Xinge Zhu +4

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 i…

cs.CV2021

Learning to Match Features with Seeded Graph Matching Network

Hongkai Chen, Zixin Luo, Jiahui Zhang +5

Matching local features across images is a fundamental problem in computer vision. Targeting towards high accuracy and efficiency, we propose Seeded Graph Matching Network, a graph…

cs.CV2021

VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation

Zeyu Hu, Xuyang Bai, Jiaxiang Shang +6

In recent years, sparse voxel-based methods have become the state-of-the-arts for 3D semantic segmentation of indoor scenes, thanks to the powerful 3D CNNs. Nevertheless, being obl…

cs.CV2021★ 17 cited

PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency

Xuyang Bai, Zixin Luo, Lei Zhou +5

Removing outlier correspondences is one of the critical steps for successful feature-based point cloud registration. Despite the increasing popularity of introducing deep learning…

cs.CV2020

JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds

Zeyu Hu, Mingmin Zhen, Xuyang Bai +2

Semantic segmentation and semantic edge detection can be seen as two dual problems with close relationships in computer vision. Despite the fast evolution of learning-based 3D sema…