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

  title={SN-Graph: A Minimalist 3D Object Representation for Classification},
  author={Siyu Zhang and Hui Cao and Yuqi Liu and Shen Cai and Yanting Zhang and Yuanzhan Li and Xiaoyu Chi},
  journal={2021 IEEE International Conference on Multimedia and Expo (ICME)},
  • Siyu ZhangH. Cao Xiaoyu Chi
  • Published 31 May 2021
  • Computer Science
  • 2021 IEEE International Conference on Multimedia and Expo (ICME)
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… 

Figures and Tables from this paper

An Efficient End-to-End 3D Voxel Reconstruction based on Neural Architecture Search

This paper proposes an efficient voxel reconstruction method utilizing neural architecture search (NAS) and binary classification and completes the end-to-end network by classifying binary voxels.

High-fidelity 3D Model Compression based on Key Spheres

An SDF prediction network using explicit key spheres as input, which can significantly improve the reconstruction accuracy with a negligible storage cost and achieves the high-fidelity and high-compression 3D object coding and reconstruction.



A Graph-CNN for 3D Point Cloud Classification

  • Yingxue ZhangM. Rabbat
  • Computer Science, Mathematics
    2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2018
By the effective exploration of the point cloud local structure using the Graph-CNN, the proposed architecture achieves competitive performance on the 3D object classification benchmark ModelNet, and the architecture is more stable than competing schemes.

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.

InSphereNet: a Concise Representation and Classification Method for 3D Object

Because of the admirable spatial representation of infilling spheres, the proposed InSphereNet method can not only utilize very fewer number of spheres to accomplish classification task, but also design a lightweight In SphereNet with less layers and parameters than previous methods.

RGCNN: Regularized Graph CNN for Point Cloud Segmentation

A regularized graph convolutional neural network (RGCNN) that directly consumes point clouds is proposed that significantly reduces the computational complexity while achieving competitive performance with the state of the art.

3D ShapeNets: A deep representation for volumetric shapes

This work proposes to represent a geometric 3D shape as a probability distribution of binary variables on a 3D voxel grid, using a Convolutional Deep Belief Network, and shows that this 3D deep representation enables significant performance improvement over the-state-of-the-arts in a variety of tasks.

Efficient Learning on Point Clouds With Basis Point Sets

This work proposes basis point sets as a highly efficient and fully general way to process point clouds with machine learning algorithms and achieves performance comparable to the state-of-the-art computationally intense multi-step frameworks in one network pass that can be done in less than 1ms.

Dynamic Graph CNN for Learning on Point Clouds

This work proposes a new neural network module suitable for CNN-based high-level tasks on point clouds, including classification and segmentation called EdgeConv, which acts on graphs dynamically computed in each layer of the network.

GeoNet: Deep Geodesic Networks for Point Cloud Analysis

This work introduces GeoNet, the first deep learning architecture trained to model the intrinsic structure of surfaces represented as point clouds, and proposes fusion schemes which use GeoNet in conjunction with other baseline or backbone networks, such as PU-Net and PointNet++, for down-stream point cloud analysis.

Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolution

A brand new point-set learning framework PRIN is proposed, namely, Pointwise Rotation-Invariant Network, focusing on rotation-invariant feature extraction in point clouds analysis, which shows that, on the dataset with randomly rotated point clouds, PRIN demonstrates better performance than state-of-the-art methods without any data augmentation.

VoxNet: A 3D Convolutional Neural Network for real-time object recognition

  • Daniel MaturanaS. Scherer
  • Computer Science
    2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2015
VoxNet is proposed, an architecture to tackle the problem of robust object recognition by integrating a volumetric Occupancy Grid representation with a supervised 3D Convolutional Neural Network (3D CNN).