PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation

  title={PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation},
  author={Mohsen Yavartanoo and Shih-Hsuan Hung and Reyhaneh Neshatavar and Yue Zhang and Kyoung Mu Lee},
  journal={2021 International Conference on 3D Vision (3DV)},
3D shape representation and its processing have substantial effects on 3D shape recognition. The polygon mesh as a 3D shape representation has many advantages in computer graphics and geometry processing. However, there are still some challenges for the existing deep neural network (DNN)-based methods on polygon mesh representation, such as handling the variations in the degree and permutations of the vertices and their pairwise distances. To overcome these challenges, we propose a DNN-based… 

Figures and Tables from this paper

3D Object Recognition Method Using CNNs and Slicing

This paper proposes a strategy of feeding 2D representations of 3D meshes made by using different types of slicing to a CNN to minimize the information loss and the redundancy the data suffers going from a 3D representation to a 2D one.

Equivariant Hypergraph Neural Networks

Equivariant Hypergraph Neural Network (EHNN), the first attempt to realize maximally expressive equivariant layers for general hypergraph learning, is presented and it is shown that expressive most message passing networks are shown and empirical evidences are provided.

A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective

A comprehensive review of GNNs and graph Transformers in computer vision from a task-oriented perspective and divides their applications into categories according to the modality of input data, i.e., 2D natural images, videos, 3D data, vision + language, and medical images.



Multi-view Convolutional Neural Networks for 3D Shape Recognition

This work presents a standard CNN architecture trained to recognize the shapes' rendered views independently of each other, and shows that a 3D shape can be recognized even from a single view at an accuracy far higher than using state-of-the-art3D shape descriptors.

Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation

This work introduces a novel graph convolutional operator, acting directly on the 3D mesh, that explicitly models the inductive bias of the fixed underlying graph, by enforcing consistent local orderings of the vertices of the graph, through the spiral operator.

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.

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.

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.

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.

DeepPano: Deep Panoramic Representation for 3-D Shape Recognition

This letter introduces a robust representation of 3-D shapes, named DeepPano, learned with deep convolutional neural networks (CNN), where a row-wise max-pooling layer is inserted between the convolution and fully-connected layers, making the learned representations invariant to the rotation around a principle axis.

MeshWalker: Deep Mesh Understanding by Random Walks

This paper proposes a very different approach, termed MeshWalker, to learn the shape directly from a given mesh, by random walks along the surface, which "explore" the mesh's geometry and topology.

SPNet: Deep 3D Object Classification and Retrieval using Stereographic Projection

An efficient Stereographic Projection Neural Network (SPNet) for learning representations of 3D objects that performs comparably to the state-of-the-art methods while having substantially lower GPU memory as well as network parameters is proposed.

LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networks

  • Sudhakar KumawatS. Raman
  • Computer Science
    2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
The ReLPV block provides significant parameter savings and improves the state-of-the-art on the UCF-101 split-1 action recognition dataset by 5.68% (when trained from scratch) while using only 15% of the parameters of the state of the art.