Fully-Geometric Cross-Attention for Point Cloud Registration

• URL: http://arxiv.org/abs/2502.08285v1
• Date: Wed, 12 Feb 2025 10:44:36 GMT
• Title: Fully-Geometric Cross-Attention for Point Cloud Registration
• Authors: Weijie Wang, Guofeng Mei, Jian Zhang, Nicu Sebe, Bruno Lepri, Fabio Poiesi,
• Abstract summary: Point cloud registration approaches often fail when the overlap between point clouds is low due to noisy point correspondences. This work introduces a novel cross-attention mechanism tailored for Transformer-based architectures that tackles this problem. We integrate the Gromov-Wasserstein distance into the cross-attention formulation to jointly compute distances between points across different point clouds. At the point level, we also devise a self-attention mechanism that aggregates the local geometric structure information into point features for fine matching.
• Score: 51.865371511201765
• License:
• Abstract: Point cloud registration approaches often fail when the overlap between point clouds is low due to noisy point correspondences. This work introduces a novel cross-attention mechanism tailored for Transformer-based architectures that tackles this problem, by fusing information from coordinates and features at the super-point level between point clouds. This formulation has remained unexplored primarily because it must guarantee rotation and translation invariance since point clouds reside in different and independent reference frames. We integrate the Gromov-Wasserstein distance into the cross-attention formulation to jointly compute distances between points across different point clouds and account for their geometric structure. By doing so, points from two distinct point clouds can attend to each other under arbitrary rigid transformations. At the point level, we also devise a self-attention mechanism that aggregates the local geometric structure information into point features for fine matching. Our formulation boosts the number of inlier correspondences, thereby yielding more precise registration results compared to state-of-the-art approaches. We have conducted an extensive evaluation on 3DMatch, 3DLoMatch, KITTI, and 3DCSR datasets.

Related papers

• BiEquiFormer: Bi-Equivariant Representations for Global Point Cloud Registration [28.75341781515012]
  The goal of this paper is to address the problem of global point cloud registration (PCR) i.e., finding the optimal alignment between point clouds. We show that state-of-the-art deep learning methods suffer from huge performance degradation when the point clouds are arbitrarily placed in space.
  arXiv  Detail & Related papers  (2024-07-11T17:58:10Z)
• Unleash the Potential of 3D Point Cloud Modeling with A Calibrated Local Geometry-driven Distance Metric [62.365983810610985]
  We propose a novel distance metric called Calibrated Local Geometry Distance (CLGD) CLGD computes the difference between the underlying 3D surfaces calibrated and induced by a set of reference points. As a generic metric, CLGD has the potential to advance 3D point cloud modeling.
  arXiv  Detail & Related papers  (2023-06-01T11:16:20Z)
• Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space [25.57569871876213]
  We propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space (content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class. We also introduce an Inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately.
  arXiv  Detail & Related papers  (2023-03-08T14:11:05Z)
• Learning a Task-specific Descriptor for Robust Matching of 3D Point Clouds [40.81429160296275]
  We learn a robust task-specific feature descriptor to consistently describe the correct point correspondence under interference. Our method EDFNet develops from two aspects. First, we augment the matchability of correspondences by utilizing their repetitive local structure.
  arXiv  Detail & Related papers  (2022-10-26T17:57:23Z)
• 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)
• IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment [58.8330387551499]
  We formulate the problem as estimation of point-wise trajectories (i.e., smooth curves) We propose IDEA-Net, an end-to-end deep learning framework, which disentangles the problem under the assistance of the explicitly learned temporal consistency. We demonstrate the effectiveness of our method on various point cloud sequences and observe large improvement over state-of-the-art methods both quantitatively and visually.
  arXiv  Detail & Related papers  (2022-03-22T10:14:08Z)
• PointAttN: You Only Need Attention for Point Cloud Completion [89.88766317412052]
  Point cloud completion refers to completing 3D shapes from partial 3D point clouds. We propose a novel neural network for processing point cloud in a per-point manner to eliminate kNNs. The proposed framework, namely PointAttN, is simple, neat and effective, which can precisely capture the structural information of 3D shapes.
  arXiv  Detail & Related papers  (2022-03-16T09:20:01Z)
• 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)
• SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation [71.2856098776959]
  Estimating 3D motions for point clouds is challenging, since a point cloud is unordered and its density is significantly non-uniform. We propose a novel architecture named Sparse Convolution-Transformer Network (SCTN) that equips the sparse convolution with the transformer. We show that the learned relation-based contextual information is rich and helpful for matching corresponding points, benefiting scene flow estimation.
  arXiv  Detail & Related papers  (2021-05-10T15:16:14Z)
• DeepCLR: Correspondence-Less Architecture for Deep End-to-End Point Cloud Registration [12.471564670462344]
  This work addresses the problem of point cloud registration using deep neural networks. We propose an approach to predict the alignment between two point clouds with overlapping data content, but displaced origins. Our approach achieves state-of-the-art accuracy and the lowest run-time of the compared methods.
  arXiv  Detail & Related papers  (2020-07-22T08:20:57Z)

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.