.png){kind=icon}
返回
Adaptive Multiview Graph Convolutional Network for 3-D Point Cloud Classification and Segmentation
.png){kind=icon}
PRE
AI
DOI：10.1109/TCDS.2024.3403900.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Point cloud classification and segmentation are crucial tasks for point cloud processing and have wide range of applications, such as autonomous driving and robot grasping. Some pioneering methods, including PointNet, VoxNet, and DGCNN, have made substantial advancements. However, most of these methods overlook the geometric relationships between points at large distances from different perspectives within the point cloud. This oversight constrains feature extraction capabilities and consequently limits any further improvements in classification and segmentation accuracy. To address this issue, we propose an adaptive multiview graph convolutional network (AM-GCN), which comprehensively synthesizes both the global geometric features of the point cloud and the local features within the projection planes of multiple views through an adaptive graph construction method. First, an adaptive rotation module in AM-GCN is proposed to predict a more favorable angle of view for projection. Then, a multilevel feature extraction network can flexibly be constructed by spatial-based or spectral-based graph convolution layers. Finally, AM-GCN is evaluated on ModelNet40 for classification, ShapeNetPart for part segmentation, ScanNetv2 and S3DIS for scene segmentation, which demonstrates the robustness of the AM-GCN with competitive performance compared with existing methods. It is worth noting that it performs state-of-the-art performance in many categories.
Keyword:
Point cloud compression
Three-dimensional displays
Convolution
Feature extraction
Adaptive systems
Task analysis
Semantics
Adaptive rotation
classification and segmentation
graph convolutional network (GCN)
multiview
point cloud
期刊
IF:
4.9
论文数:
1.0K
被引数:
3.5K
机构
引用论文
The thermodynamic parameters of monomer and dimer molecules of cerium and praseodymium tribromides
.png){kind=icon}
PREAI
分享收藏Spatial-Temporal Multiscale Constrained Learning for mmWave-Based Human Pose Estimation基于时空多尺度约束学习的毫米波人体姿态估计
PREAI
分享收藏A Self-Distillation Embedded Supervised Affinity Attention Model for Few-Shot Segmentation一种用于少镜头分割的自蒸馏嵌入式监督亲和力注意模型
OAAI
OAAI分享收藏
查看更多内容