DeepBBS: Deep Best Buddies for Point Cloud Registration

• URL: http://arxiv.org/abs/2110.03016v1
• Date: Wed, 6 Oct 2021 19:00:07 GMT
• Title: DeepBBS: Deep Best Buddies for Point Cloud Registration
• Authors: Itan Hezroni, Amnon Drory, Raja Giryes, Shai Avidan
• Abstract summary: DeepBBS is a novel method for learning a representation that takes into account the best buddy distance between points during training. Our experiments show improved performance compared to previous methods.
• Score: 55.12101890792121
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, several deep learning approaches have been proposed for point cloud registration. These methods train a network to generate a representation that helps finding matching points in two 3D point clouds. Finding good matches allows them to calculate the transformation between the point clouds accurately. Two challenges of these techniques are dealing with occlusions and generalizing to objects of classes unseen during training. This work proposes DeepBBS, a novel method for learning a representation that takes into account the best buddy distance between points during training. Best Buddies (i.e., mutual nearest neighbors) are pairs of points nearest to each other. The Best Buddies criterion is a strong indication for correct matches that, in turn, leads to accurate registration. Our experiments show improved performance compared to previous methods. In particular, our learned representation leads to an accurate registration for partial shapes and in unseen categories.

Related papers

• PointRegGPT: Boosting 3D Point Cloud Registration using Generative Point-Cloud Pairs for Training [90.06520673092702]
  We present PointRegGPT, boosting 3D point cloud registration using generative point-cloud pairs for training. To our knowledge, this is the first generative approach that explores realistic data generation for indoor point cloud registration.
  arXiv  Detail & Related papers  (2024-07-19T06:29:57Z)
• A Strong Baseline for Point Cloud Registration via Direct Superpoints Matching [7.308509114539376]
  We propose a simple and effective baseline to find correspondences of superpoints in a global matching manner. Our simple yet effective baseline shows comparable or even better results than state-of-the-art methods on three datasets.
  arXiv  Detail & Related papers  (2023-07-03T21:33:40Z)
• Category-Level Global Camera Pose Estimation with Multi-Hypothesis Point Cloud Correspondences [26.885846254261626]
  Correspondence search is an essential step in rigid point cloud registration algorithms. This paper proposes an optimization method that retains all possible correspondences for each keypoint when matching a partial point cloud to a complete point cloud. We also propose a new point feature descriptor that measures the similarity between local point cloud regions.
  arXiv  Detail & Related papers  (2022-09-28T21:12:51Z)
• Unsupervised Representation Learning for 3D Point Cloud Data [66.92077180228634]
  We propose a simple yet effective approach for unsupervised point cloud learning. In particular, we identify a very useful transformation which generates a good contrastive version of an original point cloud. We conduct experiments on three downstream tasks which are 3D object classification, shape part segmentation and scene segmentation.
  arXiv  Detail & Related papers  (2021-10-13T10:52:45Z)
• Point Discriminative Learning for Unsupervised Representation Learning on 3D Point Clouds [54.31515001741987]
  We propose a point discriminative learning method for unsupervised representation learning on 3D point clouds. We achieve this by imposing a novel point discrimination loss on the middle level and global level point features. Our method learns powerful representations and achieves new state-of-the-art performance.
  arXiv  Detail & Related papers  (2021-08-04T15:11:48Z)
• Robust Point Cloud Registration Framework Based on Deep Graph Matching [5.865029600972316]
  3D point cloud registration is a fundamental problem in computer vision and robotics. We propose a novel deep graph matchingbased framework for point cloud registration.
  arXiv  Detail & Related papers  (2021-03-07T04:20:29Z)
• PointCutMix: Regularization Strategy for Point Cloud Classification [7.6904253666422395]
  We propose a simple and effective augmentation method for the point cloud data, named PointCutMix. It finds the optimal assignment between two point clouds and generates new training data by replacing the points in one sample with their optimal assigned pairs.
  arXiv  Detail & Related papers  (2021-01-05T11:39:06Z)
• Best Buddies Registration for Point Clouds [46.48442376651696]
  Loss functions are inspired by the Best Buddies Similarity measure that counts the number of mutual nearest neighbors between two point sets. We present several algorithms, collectively named Best Buddy Registration (BBR), where each algorithm consists of optimizing one of these loss functions with Adam gradient descent. Experiments on various data sets, both synthetic and real, demonstrate the effectiveness of the BBR algorithms.
  arXiv  Detail & Related papers  (2020-10-05T10:49:18Z)
• Unsupervised Point Cloud Registration via Salient Points Analysis (SPA) [57.62713515497585]
  An unsupervised point cloud registration method, called salient points analysis (SPA), is proposed in this work. It first applies the PointHop++ method to point clouds, finds corresponding salient points in two point clouds based on the local surface characteristics of points and performs registration by matching the corresponding salient points. The effectiveness of the SPA method is demonstrated by experiments on seen and unseen classes and noisy point clouds from the ModelNet-40 dataset.
  arXiv  Detail & Related papers  (2020-09-02T18:40:37Z)
• 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)

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.