DCG-Net: Dynamic Capsule Graph Convolutional Network for Point Clouds

DCG-Net: Dynamic Capsule Graph Convolutional Network for Point Clouds

This article introduces DCG-Net (Dynamic Capsule Graph Network) to analyze point clouds for the tasks of classification and segmentation. DCG-Net aggregates point cloud features to build and update the graphs based on the dynamic routing mechanism of capsule networks at each layer of a convolutional...

Full description

Bibliographic Details
Main Authors: Dena Bazazian, Dhananjay Nahata
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Convolutional networks
dynamic capsule graph
point clouds
segmentation and classification
Online Access:https://ieeexplore.ieee.org/document/9226416/

Internet

https://ieeexplore.ieee.org/document/9226416/

Similar Items