Cross-Shape Graph Convolutional Networks

03/20/2020
by   Dmitry Petrov, et al.
0

We present a method that processes 3D point clouds by performing graph convolution operations across shapes. In this manner, point descriptors are learned by allowing interaction and propagation of feature representations within a shape collection. To enable this form of non-local, cross-shape graph convolution, our method learns a pairwise point attention mechanism indicating the degree of interaction between points on different shapes. Our method also learns to create a graph over shapes of an input collection whose edges connect shapes deemed as useful for performing cross-shape convolution. The edges are also equipped with learned weights indicating the compatibility of each shape pair for cross-shape convolution. Our experiments demonstrate that this interaction and propagation of point representations across shapes make them more discriminative. In particular, our results show significantly improved performance for 3D point cloud semantic segmentation compared to conventional approaches, especially in cases with the limited number of training examples.

READ FULL TEXT

page 2

page 6

page 9

page 12

research
03/30/2020

PointGMM: a Neural GMM Network for Point Clouds

Point clouds are a popular representation for 3D shapes. However, they e...
research
08/24/2019

Blended Convolution and Synthesis for Efficient Discrimination of 3D Shapes

Existing networks directly learn feature representations on 3D point clo...
research
08/29/2021

Differentiable Convolution Search for Point Cloud Processing

Exploiting convolutional neural networks for point cloud processing is q...
research
06/14/2017

Learning Local Shape Descriptors from Part Correspondences With Multi-view Convolutional Networks

We present a new local descriptor for 3D shapes, directly applicable to ...
research
10/03/2019

Learning Point Embeddings from Shape Repositories for Few-Shot Segmentation

User generated 3D shapes in online repositories contain rich information...
research
07/15/2020

Learning Part Boundaries from 3D Point Clouds

We present a method that detects boundaries of parts in 3D shapes repres...
research
07/19/2017

Shape Generation using Spatially Partitioned Point Clouds

We propose a method to generate 3D shapes using point clouds. Given a po...

Please sign up or login with your details

Forgot password? Click here to reset