Dense Graph Convolutional Neural Networks on 3D Meshes for 3D Object Segmentation and Classification

@article{Tang2021DenseGC,
  title={Dense Graph Convolutional Neural Networks on 3D Meshes for 3D Object Segmentation and Classification},
  author={Wenming Tang and Guoping Qiu},
  journal={Image Vis. Comput.},
  year={2021},
  volume={114},
  pages={104265}
}
1 Citations

A deep-learning model for semantic segmentation of meshes from UAV oblique images

A deep learning model is proposed for the mesh semantic segmentation, and graph concept and transformer blocks are employed for mesh representation and feature learning to efficiently capture local geometry and neighbourhood context within the mesh.

References

SHOWING 1-10 OF 45 REFERENCES

Towards 3D convolutional neural networks with meshes

A Graph Convolutional Neural Network (Graph-CNN) is proposed, which enables mesh data to be represented exactly (not approximately as with voxels) with quadratic growth as the number of vertices increases.

FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis

This work proposes a novel graph-convolution operator to establish correspondences between filter weights and graph neighborhoods with arbitrary connectivity, and obtains excellent experimental results that significantly improve over previous state-of-the-art shape correspondence results.

MeshNet: Mesh Neural Network for 3D Shape Representation

Experimental results and comparisons with the state-of-the-art methods demonstrate that the proposed MeshNet can achieve satisfying 3D shape classification and retrieval performance, which indicates the effectiveness of the proposed method on3D shape representation.

Primal-Dual Mesh Convolutional Neural Networks

This work extends a primal-dual framework drawn from the graph-neural-network literature to triangle meshes, and defines convolutions on two types of graphs constructed from an input mesh, and introduces a pooling operation that allows handling variations in the mesh connectivity by clustering mesh faces in a task-driven fashion.

Active 3-D Shape Cosegmentation With Graph Convolutional Networks

An active learning strategy that queries the most informative samples to extend the initial training samples of GCN to generate more accurate predictions of the method, as well as demonstrating the effectiveness of the approach on the Shape COSEG dataset.

MeshCNN: a network with an edge

This paper utilizes the unique properties of the mesh for a direct analysis of 3D shapes using MeshCNN, a convolutional neural network designed specifically for triangular meshes, and demonstrates the effectiveness of MeshCNN on various learning tasks applied to 3D meshes.

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.

Convolutional neural networks on surfaces via seamless toric covers

This paper presents a method for applying deep learning to sphere-type shapes using a global seamless parameterization to a planar flat-torus, for which the convolution operator is well defined and the standard deep learning framework can be readily applied for learning semantic, high-level properties of the shape.

View-GCN: View-Based Graph Convolutional Network for 3D Shape Analysis

  • Xin WeiRuixuan YuJian Sun
  • Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
A novel view-based Graph Convolutional Neural Network, dubbed as view-GCN, to recognize 3D shape based on graph representation of multiple views in flexible view configurations, which is a hierarchical network based on local and non-local graph convolution for feature transform, and selective view-sampling for graph coarsening.

Deep Learning 3D Shape Surfaces Using Geometry Images

This work qualitatively and quantitatively validate that creating geometry images using authalic parametrization on a spherical domain is suitable for robust learning of 3D shape surfaces, and proposes a way to implicitly learn the topology and structure of3D shapes using geometry images encoded with suitable features.