Local-Global based Deep Registration Neural Network for Rigid Alignment

Victor Villena-Martinez, Marcelo Saval-Calvo, Jorge Azorin-Lopez, Andres Fuster-Guillo, Robert B Fisher

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Three-dimensional registration is a well-known topic in computer vision that aims to align two datasets (e.g. point clouds). Recent approaches to this problem are based on learning techniques. In this paper, we present an improved solution to the problem of registration with a novel architecture that, given two 3D point clouds as input, estimates the rotation to map one into the other. The network architecture is conceptually divided into two parts, the first part is a feature selection based on PointNet and PointNet++. The second part estimates the rotation with Euler angles by calculating the correspondences with a FlowNet-based network, and finally the rotations in yaw, pitch, and roll. The generalization capability of the proposal allows mapping two point clouds in a wide range of angles with a stable error over the whole range. Experiments have been carried out using the ModelNet10 objects dataset, varying the axis and the angle of rotation to provide a sufficiently complete evaluation of the architecture. The results show an average distance Mean Square Error of 4.94E-05 within a unit sphere and a rotation error of 1.18 degrees. The results with noisy point clouds are sufficiently accurate providing the network was trained only with noise-free data, demonstrating good generalization of the approach
Original languageEnglish
Title of host publication2021 International Joint Conference on Neural Networks (IJCNN)
Number of pages13
ISBN (Electronic)978-1-6654-3900-8
ISBN (Print)978-1-6654-4597-9
Publication statusPublished - 20 Sept 2021
EventThe International Joint Conference on Neural Networks - Online
Duration: 18 Jul 202122 Jul 2021

Publication series

ISSN (Print)2161-4393
ISSN (Electronic)2161-4407


ConferenceThe International Joint Conference on Neural Networks
Abbreviated titleIJCNN 2021
Internet address

Keywords / Materials (for Non-textual outputs)

  • Deep Registration Networks
  • 3d registration network
  • deep learning
  • point cloud registration


Dive into the research topics of 'Local-Global based Deep Registration Neural Network for Rigid Alignment'. Together they form a unique fingerprint.

Cite this