KdO-Net: Towards Improving the Efficiency of Deep Convolutional Neural Networks Applied in the 3D Pairwise Point Feature Matching

KdO-Net: Towards Improving the Efficiency of Deep Convolutional Neural Networks Applied in the 3D Pairwise Point Feature Matching

In this work, we construct a Kd–Octree hybrid index structure to organize the point cloud and generate patch-based feature descriptors at its leaf nodes. We propose a simple yet effective convolutional neural network, termed KdO-Net, with Kd–Octree based descriptors as input for 3D pairwise point cl...

Full description

Bibliographic Details
Main Authors: Rui Zhang, Guangyun Li, Wolfgang Wiedemann, Christoph Holst
Format: Article
Language:English
Published: MDPI AG 2022-06-01
Series:Remote Sensing
Subjects:
point cloud
feature matching
point cloud registration
deep learning
nearest neighbor searching
Online Access:https://www.mdpi.com/2072-4292/14/12/2883

Internet

https://www.mdpi.com/2072-4292/14/12/2883

Similar Items