Indirect Point Cloud Registration: Aligning Distance Fields Using a Pseudo Third Point Set
- 10 June 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (3) , 7075-7082
Abstract
In recent years, implicit functions have drawn attention in the field of 3D reconstruction and have successfully been applied with Deep Learning. However, for incremental reconstruction, implicit function-based registrations have been rarely explored. Inspired by the high precision of deep learning global feature registration, we propose to combine this with distance fields. We generalize the algorithm to a non-Deep Learning setting while retaining the accuracy. Our algorithm is more accurate than conventional models while, without any training, it achieves a competitive performance and faster speed, compared to Deep Learning-based registration models. The implementation is available on github1 for the research community.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- PointNetLK: Robust & Efficient Point Cloud Registration Using PointNet2019
- 3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration2018
- 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions2017
- SDF-2-SDF: Highly Accurate 3D Object Reconstruction2016
- Multi-Robot Localization and Mapping Based on Signed Distance FunctionsJournal of Intelligent & Robotic Systems, 2016
- SDF-TAR: Parallel Tracking and Refinement in RGB-D Data using Volumetric Registration2016
- 3D ShapeNets: A deep representation for volumetric shapes2015
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012
- Generalized-ICP2009
- A method for registration of 3-D shapesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992