Iterative BTreeNet: Unsupervised learning for large and dense 3D point cloud registration
Authors: Xi, L., Tang, W., Xue, T. and Wan, T.R.
Journal: Neurocomputing
Volume: 506
Pages: 336-354
eISSN: 1872-8286
ISSN: 0925-2312
DOI: 10.1016/j.neucom.2022.07.082
Abstract:3D point cloud registration is a computational process that aligns two 3D point clouds through transformation. i.e. finding matching translation and rotation. Existing state-of-the-art learning-based methods require ground-truth transformation as supervision and often perform poorly in dealing with partial point clouds and large scenes that are not trained, resulting in poor generalization for neural networks. In this paper, we propose a novel unsupervised deep learning network - Binary Tree Network (BTreeNet) that consists of a novel forward propagation, which learns features for the rotation separately from the translation and avoids the interference between the estimations of rotation and translation in one single matrix. We then propose an Iterative Binary Tree Network (IBTreeNet) to continuously improve the registration accuracy for large and dense 3D point clouds. The Chamfer Distance and the Earth Mover's Distance are adopted as the loss function for unsupervised learning. We show that BTreeNet and IBTreeNet outperform state-of-the-art learning-based and traditional methods on partial and noisy point clouds without training them in such scenarios. Most importantly, the proposed methods exhibit remarkable generalization and robustness to unseen large and dense scenes that are never trained.
https://eprints.bournemouth.ac.uk/37447/
Source: Scopus
Iterative BTreeNet: Unsupervised learning for large and dense 3D point cloud registration
Authors: Xi, L., Tang, W., Xue, T. and Wan, T.
Journal: NEUROCOMPUTING
Volume: 506
Pages: 336-354
eISSN: 1872-8286
ISSN: 0925-2312
DOI: 10.1016/j.neucom.2022.07.082
https://eprints.bournemouth.ac.uk/37447/
Source: Web of Science (Lite)
Iterative BTreeNet: Unsupervised learning for large and dense 3D point cloud registration
Authors: Xi, L., Tang, W., Xue, T. and Wan, T.R.
Journal: Neurocomputing
Volume: 506
Issue: September
Pages: 336-354
ISSN: 0925-2312
Abstract:3D point cloud registration is a computational process that aligns two 3D point clouds through transformation. i.e. finding matching translation and rotation. Existing state-of-the-art learning-based methods require ground-truth transformation as supervision and often perform poorly in dealing with partial point clouds and large scenes that are not trained, resulting in poor generalization for neural networks. In this paper, we propose a novel unsupervised deep learning network - Binary Tree Network (BTreeNet) that consists of a novel forward propagation, which learns features for the rotation separately from the translation and avoids the interference between the estimations of rotation and translation in one single matrix. We then propose an Iterative Binary Tree Network (IBTreeNet) to continuously improve the registration accuracy for large and dense 3D point clouds. The Chamfer Distance and the Earth Mover's Distance are adopted as the loss function for unsupervised learning. We show that BTreeNet and IBTreeNet outperform state-of-the-art learning-based and traditional methods on partial and noisy point clouds without training them in such scenarios. Most importantly, the proposed methods exhibit remarkable generalization and robustness to unseen large and dense scenes that are never trained.
https://eprints.bournemouth.ac.uk/37447/
Source: BURO EPrints