PAI-GCN: Permutable Anisotropic Graph Convolutional Networks for 3D Shape Representation Learning

04/21/2020
by   Zhongpai Gao, et al.
0

Demand for efficient 3D shape representation learning is increasing in many 3D computer vision applications. The recent success of convolutional neural networks (CNNs) for image analysis suggests the value of adapting insight from CNN to 3D shapes. However, unlike images that are Euclidean structured, 3D shape data are irregular since each node's neighbors are inconsistent. Various convolutional graph neural networks for 3D shapes have been developed using isotropic filters or using anisotropic filters with predefined local coordinate systems to overcome the node inconsistency on graphs. However, isotropic filters or predefined local coordinate systems limit the representation power. In this paper, we propose a permutable anisotropic convolutional operation (PAI-Conv) that learns adaptive soft-permutation matrices for each node according to the geometric shape of its neighbors and performs shared anisotropic filters as CNN does. Comprehensive experiments demonstrate that our model produces significant improvement in 3D shape reconstruction compared to state-of-the-art methods.

READ FULL TEXT
research
05/27/2020

PAI-Conv: Permutable Anisotropic Convolutional Networks for Learning on Point Clouds

Demand for efficient representation learning on point clouds is increasi...
research
09/11/2019

Geometric Graph Convolutional Neural Networks

Graph Convolutional Networks (GCNs) have recently become the primary cho...
research
01/22/2022

Overcoming Oversmoothness in Graph Convolutional Networks via Hybrid Scattering Networks

Geometric deep learning (GDL) has made great strides towards generalizin...
research
02/03/2018

GeniePath: Graph Neural Networks with Adaptive Receptive Paths

We present, GeniePath, a scalable approach for learning adaptive recepti...
research
03/25/2019

Structured 2D Representation of 3D Data for Shape Processing

We represent 3D shape by structured 2D representations of fixed length m...
research
01/26/2015

Geodesic convolutional neural networks on Riemannian manifolds

Feature descriptors play a crucial role in a wide range of geometry anal...
research
12/14/2016

Beam Search for Learning a Deep Convolutional Neural Network of 3D Shapes

This paper addresses 3D shape recognition. Recent work typically represe...

Please sign up or login with your details

Forgot password? Click here to reset