Spherical Message Passing for 3D Graph Networks

• URL: http://arxiv.org/abs/2102.05013v1
• Date: Tue, 9 Feb 2021 18:31:23 GMT
• Title: Spherical Message Passing for 3D Graph Networks
• Authors: Yi Liu, Limei Wang, Meng Liu, Xuan Zhang, Bora Oztekin, Shuiwang Ji
• Abstract summary: We consider representation learning from 3D graphs in which each node is associated with a spatial position in 3D. We propose a generic framework, known as the 3D graph network (3DGN), to provide a unified interface at different levels of granularity for 3D graphs. We derive physically-based representations of geometric information and propose the SphereNet for learning representations of 3D graphs.
• Score: 40.10938363608572
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider representation learning from 3D graphs in which each node is associated with a spatial position in 3D. This is an under explored area of research, and a principled framework is currently lacking. In this work, we propose a generic framework, known as the 3D graph network (3DGN), to provide a unified interface at different levels of granularity for 3D graphs. Built on 3DGN, we propose the spherical message passing (SMP) as a novel and specific scheme for realizing the 3DGN framework in the spherical coordinate system (SCS). We conduct formal analyses and show that the relative location of each node in 3D graphs is uniquely defined in the SMP scheme. Thus, our SMP represents a complete and accurate architecture for learning from 3D graphs in the SCS. We derive physically-based representations of geometric information and propose the SphereNet for learning representations of 3D graphs. We show that existing 3D deep models can be viewed as special cases of the SphereNet. Experimental results demonstrate that the use of complete and accurate 3D information in 3DGN and SphereNet leads to significant performance improvements in prediction tasks.

Related papers

• 3D Geometry-aware Deformable Gaussian Splatting for Dynamic View Synthesis [49.352765055181436]
  We propose a 3D geometry-aware deformable Gaussian Splatting method for dynamic view synthesis. Our solution achieves 3D geometry-aware deformation modeling, which enables improved dynamic view synthesis and 3D dynamic reconstruction.
  arXiv  Detail & Related papers  (2024-04-09T12:47:30Z)
• Dense Graph Convolutional Neural Networks on 3D Meshes for 3D Object Segmentation and Classification [0.0]
  We present new designs of graph convolutional neural networks (GCNs) on 3D meshes for 3D object classification and segmentation. We use the faces of the mesh as basic processing units and represent a 3D mesh as a graph where each node corresponds to a face.
  arXiv  Detail & Related papers  (2021-06-30T02:17:16Z)
• SN-Graph: a Minimalist 3D Object Representation for Classification [4.145824494809195]
  In this paper, we propose a Sphere Node Graph (SN-Graph) to represent 3D objects. Specifically, we extract a certain number of internal spheres (as nodes) from the signed distance field (SDF), and then establish connections (as edges) among the sphere nodes to construct a graph. Experiments conducted on the ModelNet40 dataset show that when there are fewer nodes in the graph or the tested objects are rotated arbitrarily, the classification accuracy of SN-Graph is significantly higher.
  arXiv  Detail & Related papers  (2021-05-31T08:24:09Z)
• Concentric Spherical GNN for 3D Representation Learning [53.45704095146161]
  We propose a novel multi-resolution convolutional architecture for learning over concentric spherical feature maps. Our hierarchical architecture is based on alternatively learning to incorporate both intra-sphere and inter-sphere information. We demonstrate the effectiveness of our approach in improving state-of-the-art performance on 3D classification tasks with rotated data.
  arXiv  Detail & Related papers  (2021-03-18T19:05:04Z)
• Interactive Annotation of 3D Object Geometry using 2D Scribbles [84.51514043814066]
  In this paper, we propose an interactive framework for annotating 3D object geometry from point cloud data and RGB imagery. Our framework targets naive users without artistic or graphics expertise.
  arXiv  Detail & Related papers  (2020-08-24T21:51:29Z)
• Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation [87.54570024320354]
  State-of-the-art methods for large-scale driving-scene LiDAR semantic segmentation often project and process the point clouds in the 2D space. A straightforward solution to tackle the issue of 3D-to-2D projection is to keep the 3D representation and process the points in the 3D space. We develop a 3D cylinder partition and a 3D cylinder convolution based framework, termed as Cylinder3D, which exploits the 3D topology relations and structures of driving-scene point clouds.
  arXiv  Detail & Related papers  (2020-08-04T13:56:19Z)
• Distance-Geometric Graph Convolutional Network (DG-GCN) for Three-Dimensional (3D) Graphs [0.8722210937404288]
  We propose a message-passing graph convolutional network based on the distance-geometric graph representation: DG-GCN. It enables learning of filter weights from distances, thereby incorporating the geometry of 3D graphs in graph convolutions. Our work demonstrates the utility and value of DG-GCN for end-to-end deep learning on 3D graphs, particularly molecular graphs.
  arXiv  Detail & Related papers  (2020-07-06T15:20:52Z)
• Learning Local Neighboring Structure for Robust 3D Shape Representation [143.15904669246697]
  Representation learning for 3D meshes is important in many computer vision and graphics applications. We propose a local structure-aware anisotropic convolutional operation (LSA-Conv) Our model produces significant improvement in 3D shape reconstruction compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-04-21T13:40:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.