mlsanityData to 7 Oct 2026

SN-Graph: a Minimalist 3D Object Representation for Classification

arXiv 2105.14784 ↗First posted 31 May 2021cs.CV cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Using deep learning techniques to process 3D objects has achieved many successes. However, few methods focus on the representation of 3D objects, which could be more effective for specific tasks than traditional representations, such as point clouds, voxels, and multi-view images. 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, which is seamlessly suitable for 3D analysis using graph neural network (GNN). 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 than the state-of-the-art methods.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 16 of its 22 references that are in the map. First posted on arXiv 31 May 2021.

Builds on

16 of 22 references.

References · 16

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2018How Powerful are Graph Neural Networks?cited by 4,355
  6. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,682
  7. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  10. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  11. 2019Efficient Learning on Point Clouds with Basis Point Setscited by 101
  12. 2018RGCNN: Regularized Graph CNN for Point Cloud Segmentationcited by 70
4 more
  1. 2018A Graph-CNN for 3D Point Cloud Classificationcited by 49
  2. 2018Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolutioncited by 16
  3. 2019GeoNet: Deep Geodesic Networks for Point Cloud Analysiscited by 11
  4. 2019InSphereNet: a Concise Representation and Classification Method for 3D Objectcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 2.

2 papers.

  1. 2022High-fidelity 3D Model Compression based on Key Spherescited by 3
  2. 2022An Efficient End-to-End 3D Voxel Reconstruction based on Neural Architecture Searchcited by 0