Overlap Bias Matching is Necessary for Point Cloud Registration
- URL: http://arxiv.org/abs/2308.09364v1
- Date: Fri, 18 Aug 2023 07:47:22 GMT
- Title: Overlap Bias Matching is Necessary for Point Cloud Registration
- Authors: Pengcheng Shi, Jie Zhang, Haozhe Cheng, Junyang Wang, Yiyang Zhou,
Chenlin Zhao, Jihua Zhu
- Abstract summary: Overlap between point clouds to be registered may be relatively small.
We propose an unsupervised network Overlap Bias Matching Network (OBMNet) for partial point cloud registration.
- Score: 21.584033532099134
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Point cloud registration is a fundamental problem in many domains.
Practically, the overlap between point clouds to be registered may be
relatively small. Most unsupervised methods lack effective initial evaluation
of overlap, leading to suboptimal registration accuracy. To address this issue,
we propose an unsupervised network Overlap Bias Matching Network (OBMNet) for
partial point cloud registration. Specifically, we propose a plug-and-play
Overlap Bias Matching Module (OBMM) comprising two integral components, overlap
sampling module and bias prediction module. These two components are utilized
to capture the distribution of overlapping regions and predict bias
coefficients of point cloud common structures, respectively. Then, we integrate
OBMM with the neighbor map matching module to robustly identify correspondences
by precisely merging matching scores of points within the neighborhood, which
addresses the ambiguities in single-point features. OBMNet can maintain
efficacy even in pair-wise registration scenarios with low overlap ratios.
Experimental results on extensive datasets demonstrate that our approach's
performance achieves a significant improvement compared to the state-of-the-art
registration approach.
Related papers
- DBDNet:Partial-to-Partial Point Cloud Registration with Dual Branches
Decoupling [15.382633946370978]
We propose an effective registration method with dual branches decoupling for partial-to-partial registration, dubbed as DBDNet.
We present an overlap predictor that benefits from explicit feature interaction, which is achieved by the powerful attention mechanism to accurately predict pointwise masks.
We design a multi-resolution feature extraction network to capture both local and global patterns thus enhancing both overlap prediction and registration module.
arXiv Detail & Related papers (2023-10-18T06:09:12Z) - Unsupervised Deep Probabilistic Approach for Partial Point Cloud
Registration [74.53755415380171]
Deep point cloud registration methods face challenges to partial overlaps and rely on labeled data.
We propose UDPReg, an unsupervised deep probabilistic registration framework for point clouds with partial overlaps.
Our UDPReg achieves competitive performance on the 3DMatch/3DLoMatch and ModelNet/ModelLoNet benchmarks.
arXiv Detail & Related papers (2023-03-23T14:18:06Z) - Overlap-guided Gaussian Mixture Models for Point Cloud Registration [61.250516170418784]
Probabilistic 3D point cloud registration methods have shown competitive performance in overcoming noise, outliers, and density variations.
This paper proposes a novel overlap-guided probabilistic registration approach that computes the optimal transformation from matched Gaussian Mixture Model (GMM) parameters.
arXiv Detail & Related papers (2022-10-17T08:02:33Z) - Learning to Register Unbalanced Point Pairs [10.369750912567714]
Recent 3D registration methods can effectively handle large-scale or partially overlapping point pairs.
We present a novel 3D registration method, called UPPNet, for the unbalanced point pairs.
arXiv Detail & Related papers (2022-07-09T08:03:59Z) - CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud
Registration [35.57761839361479]
CoFiNet - Coarse-to-Fine Network - extracts hierarchical correspondences from coarse to fine without keypoint detection.
Our model learns to match down-sampled nodes whose vicinity points share more overlap.
Point correspondences are then refined from the overlap areas of corresponding patches, by a density-adaptive matching module.
arXiv Detail & Related papers (2021-10-26T23:05:00Z) - PCAM: Product of Cross-Attention Matrices for Rigid Registration of
Point Clouds [79.99653758293277]
PCAM is a neural network whose key element is a pointwise product of cross-attention matrices.
We show that PCAM achieves state-of-the-art results among methods which, like us, solve steps (a) and (b) jointly via deepnets.
arXiv Detail & Related papers (2021-10-04T09:23:27Z) - Consistent Two-Flow Network for Tele-Registration of Point Clouds [74.51029406361997]
We present a learning-based technique that allows registration between point clouds, presented in arbitrary poses, and having little or even no overlap.
Our technique is based on a novel neural network design that learns a prior of a class of shapes and can complete a partial shape.
We show that, compared with each separate flow, this two-flow training leads to robust and reliable tele-registration.
arXiv Detail & Related papers (2021-06-01T09:03:21Z) - RPM-Net: Robust Point Matching using Learned Features [79.52112840465558]
RPM-Net is a less sensitive and more robust deep learning-based approach for rigid point cloud registration.
Unlike some existing methods, our RPM-Net handles missing correspondences and point clouds with partial visibility.
arXiv Detail & Related papers (2020-03-30T13:45:27Z) - Learning multiview 3D point cloud registration [74.39499501822682]
We present a novel, end-to-end learnable, multiview 3D point cloud registration algorithm.
Our approach outperforms the state-of-the-art by a significant margin, while being end-to-end trainable and computationally less costly.
arXiv Detail & Related papers (2020-01-15T03:42:14Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.