Corpus ID: 128358874

Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features

@article{Zhang2019LinkedDG,
  title={Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features},
  author={Kuangen Zhang and Ming Hao and J. Wang and C. D. Silva and C. Fu},
  journal={ArXiv},
  year={2019},
  volume={abs/1904.10014}
}
Learning on point cloud is eagerly in demand because the point cloud is a common type of geometric data and can aid robots to understand environments robustly. [...] Key Method We remove the transformation network, link hierarchical features from dynamic graphs, freeze feature extractor, and retrain the classifier to increase the performance of LDGCNN. We explain our network using theoretical analysis and visualization. Through experiments, we show that the proposed LDGCNN achieves state-of-art performance on…Expand
36 Citations
GGM-Net: Graph Geometric Moments Convolution Neural Network for Point Cloud Shape Classification
  • 4
  • Highly Influenced
  • PDF
Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks
  • Siddharth Srivastava, G. Sharma
  • Computer Science
  • ArXiv
  • 2021
  • PDF
Cross-Shape Graph Convolutional Networks
  • 1
  • PDF
Grid-GCN for Fast and Scalable Point Cloud Learning
  • 24
  • PDF
A Review of Deep Learning-Based Semantic Segmentation for Point Cloud
  • 16
  • Highly Influenced
  • PDF
Multi-Head Self-Attention for 3D Point Cloud Classification
  • PDF
Regularization Strategy for Point Cloud via Rigidly Mixed Sample
  • 1
  • PDF
...
1
2
3
4
...

References

SHOWING 1-10 OF 33 REFERENCES
Dynamic Graph CNN for Learning on Point Clouds
  • 1,056
  • Highly Influential
  • PDF
Modeling Local Geometric Structure of 3D Point Clouds Using Geo-CNN
  • 45
  • PDF
Graph Neural Networks: A Review of Methods and Applications
  • 733
  • PDF
SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters
  • 248
  • Highly Influential
  • PDF
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
  • 3,704
  • Highly Influential
  • PDF
PointCNN: Convolution On X-Transformed Points
  • 551
  • PDF
SO-Net: Self-Organizing Network for Point Cloud Analysis
  • 366
  • PDF
Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models
  • 510
  • PDF
...
1
2
3
4
...