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

arXiv: https://arxiv.org/abs/1904.10014 · HTML: https://mlsanity.com/paper/1904.10014/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2019.

## Built on by (most cited first, 30 of 31)

- [Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline](https://mlsanity.com/paper/2106.05304/) (2021)
- [Regularization Strategy for Point Cloud via Rigidly Mixed Sample](https://mlsanity.com/paper/2102.01929/) (2021)
- [Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis](https://mlsanity.com/paper/2203.03311/) (2022)
- [PVT: Point-Voxel Transformer for Point Cloud Learning](https://mlsanity.com/paper/2108.06076/) (2021)
- [PatchFormer: An Efficient Point Transformer with Patch Attention](https://mlsanity.com/paper/2111.00207/) (2021)
- [Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlook](https://mlsanity.com/paper/2311.02608/) (2023)
- [DRINet++: Efficient Voxel-as-point Point Cloud Segmentation](https://mlsanity.com/paper/2111.08318/) (2021)
- [DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentation](https://mlsanity.com/paper/2108.04023/) (2021)
- [MetaSets: Meta-Learning on Point Sets for Generalizable Representations](https://mlsanity.com/paper/2204.07311/) (2022)
- [Towards Efficient Graph Convolutional Networks for Point Cloud Handling](https://mlsanity.com/paper/2104.05706/) (2021)
- [PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features](https://mlsanity.com/paper/2102.12093/) (2021)
- [Feature Transportation Improves Graph Neural Networks](https://mlsanity.com/paper/2307.16092/) (2023)
- [Attribute Artifacts Removal for Geometry-based Point Cloud Compression](https://mlsanity.com/paper/2112.00560/) (2021)
- [HyperPocket: Generative Point Cloud Completion](https://mlsanity.com/paper/2102.05973/) (2021)
- [Depth Completion using Geometry-Aware Embedding](https://mlsanity.com/paper/2203.10912/) (2022)
- [DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds](https://mlsanity.com/paper/2111.08799/) (2021)
- [Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks](https://mlsanity.com/paper/2103.15226/) (2021)
- [On The Temporal Domain of Differential Equation Inspired Graph Neural Networks](https://mlsanity.com/paper/2401.11074/) (2024)
- [Efficient Point Clouds Upsampling via Flow Matching](https://mlsanity.com/paper/2501.15286/) (2025)
- [Generating Unrestricted 3D Adversarial Point Clouds](https://mlsanity.com/paper/2111.08973/) (2021)
- [Revisiting 2D Convolutional Neural Networks for Graph-based Applications](https://mlsanity.com/paper/2105.11016/) (2021)
- [Robust Pooling through the Data Mode](https://mlsanity.com/paper/2106.10850/) (2021)
- [Structure-Aware Multi-Hop Graph Convolution for Graph Neural Networks](https://mlsanity.com/paper/2112.01714/) (2021)
- [UniDA3D: Unified Domain Adaptive 3D Semantic Segmentation Pipeline](https://mlsanity.com/paper/2212.10390/) (2022)
- [Cloud-RAIN: Point Cloud Analysis with Reflectional Invariance](https://mlsanity.com/paper/2305.07814/) (2023)
- [A Convolutional Architecture for 3D Model Embedding](https://mlsanity.com/paper/2103.03764/) (2021)
- [Shrinking unit: a Graph Convolution-Based Unit for CNN-like 3D Point Cloud Feature Extractors](https://mlsanity.com/paper/2209.12770/) (2022)
- [Learning Latent Part-Whole Hierarchies for Point Clouds](https://mlsanity.com/paper/2211.07082/) (2022)
- [Attention-based Graph Convolution Fusing Latent Structures and Multiple Features for Graph Neural Networks](https://mlsanity.com/paper/2303.00944/) (2023)
- [MLGCN: An Ultra Efficient Graph Convolution Neural Model For 3D Point Cloud Analysis](https://mlsanity.com/paper/2303.17748/) (2023)

## Abstract (arXiv)

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. However, the point cloud is sparse, unstructured, and unordered, which cannot be recognized accurately by a traditional convolutional neural network (CNN) nor a recurrent neural network (RNN). Fortunately, a graph convolutional neural network (Graph CNN) can process sparse and unordered data. Hence, we propose a linked dynamic graph CNN (LDGCNN) to classify and segment point cloud directly in this paper. 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 two standard datasets: ModelNet40 and ShapeNet.