3DRegNet: A Deep Neural Network for 3D Point Registration
Authors:
Top Cited Papers
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7191-7201
Abstract
We present 3DRegNet, a novel deep learning architecture for the registration of 3D scans. Given a set of 3D point correspondences, we build a deep neural network to address the following two challenges: (i) classification of the point correspondences into inliers/outliers, and (ii) regression of the motion parameters that align the scans into a common reference frame. With regard to regression, we present two alternative approaches: (i) a Deep Neural Network (DNN) registration and (ii) a Procrustes approach using SVD to estimate the transformation. Our correspondence-based approach achieves a higher speedup compared to competing baselines. We further propose the use of a refinement network, which consists of a smaller 3DRegNet as a refinement to improve the accuracy of the registration. Extensive experiments on two challenging datasets demonstrate that we outperform other methods and achieve state-of-the-art results. The code is available.Keywords
All Related Versions
This publication has 48 references indexed in Scilit:
- Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set RegistrationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization2015
- Registration with the Point Cloud Library: A Modular Framework for Aligning in 3-DIEEE Robotics & Automation Magazine, 2015
- Super 4PCS Fast Global Pointcloud Registration via Smart IndexingComputer Graphics Forum, 2014
- Real-time non-rigid reconstruction using an RGB-D cameraACM Transactions on Graphics, 2014
- A Stochastic Iterative Closest Point Algorithm (stochastICP)Lecture Notes in Computer Science, 2001
- A method for registration of 3-D shapesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992
- Least-squares estimation of transformation parameters between two point patternsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1991
- Random sample consensusCommunications of the ACM, 1981
- A Generalized Solution of the Orthogonal Procrustes ProblemPsychometrika, 1966