Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration

• URL: http://arxiv.org/abs/2303.13290v1
• Date: Thu, 23 Mar 2023 14:18:06 GMT
• Title: Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration
• Authors: Guofeng Mei and Hao Tang and Xiaoshui Huang and Weijie Wang and Juan Liu and Jian Zhang and Luc Van Gool and Qiang Wu
• Abstract summary: 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.
• Score: 74.53755415380171
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep point cloud registration methods face challenges to partial overlaps and rely on labeled data. To address these issues, we propose UDPReg, an unsupervised deep probabilistic registration framework for point clouds with partial overlaps. Specifically, we first adopt a network to learn posterior probability distributions of Gaussian mixture models (GMMs) from point clouds. To handle partial point cloud registration, we apply the Sinkhorn algorithm to predict the distribution-level correspondences under the constraint of the mixing weights of GMMs. To enable unsupervised learning, we design three distribution consistency-based losses: self-consistency, cross-consistency, and local contrastive. The self-consistency loss is formulated by encouraging GMMs in Euclidean and feature spaces to share identical posterior distributions. The cross-consistency loss derives from the fact that the points of two partially overlapping point clouds belonging to the same clusters share the cluster centroids. The cross-consistency loss allows the network to flexibly learn a transformation-invariant posterior distribution of two aligned point clouds. The local contrastive loss facilitates the network to extract discriminative local features. Our UDPReg achieves competitive performance on the 3DMatch/3DLoMatch and ModelNet/ModelLoNet benchmarks.

Related papers

• Mixing-Denoising Generalizable Occupancy Networks [10.316008740970037]
  Current state-of-the-art implicit neural shape models rely on the inductive bias of convolutions. We relax the intrinsic model bias and constrain the hypothesis space instead with an auxiliary regularization related to the reconstruction task. The resulting model is the first only-MLP locally conditioned reconstruction from point cloud network.
  arXiv  Detail & Related papers  (2023-11-20T19:05:57Z)
• Overlap Bias Matching is Necessary for Point Cloud Registration [21.584033532099134]
  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.
  arXiv  Detail & Related papers  (2023-08-18T07:47:22Z)
• Clustering based Point Cloud Representation Learning for 3D Analysis [80.88995099442374]
  We propose a clustering based supervised learning scheme for point cloud analysis. Unlike current de-facto, scene-wise training paradigm, our algorithm conducts within-class clustering on the point embedding space. Our algorithm shows notable improvements on famous point cloud segmentation datasets.
  arXiv  Detail & Related papers  (2023-07-27T03:42:12Z)
• Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentation [80.07161039753043]
  Weakly-supervised point cloud segmentation with extremely limited labels is desirable to alleviate the expensive costs of collecting densely annotated 3D points. This paper explores applying the consistency regularization that is commonly used in weakly-supervised learning, for its point cloud counterpart with multiple data-specific augmentations. We propose a novel Reliability-Adaptive Consistency Network (RAC-Net) to use both prediction confidence and model uncertainty to measure the reliability of pseudo labels.
  arXiv  Detail & Related papers  (2023-03-09T10:41:57Z)
• 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)
• 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)
• DeepGMR: Learning Latent Gaussian Mixture Models for Registration [113.74060941036664]
  Point cloud registration is a fundamental problem in 3D computer vision, graphics and robotics. In this paper, we introduce Deep Gaussian Mixture Registration (DeepGMR), the first learning-based registration method. Our proposed method shows favorable performance when compared with state-of-the-art geometry-based and learning-based registration methods.
  arXiv  Detail & Related papers  (2020-08-20T17:25:16Z)
• PointGMM: a Neural GMM Network for Point Clouds [83.9404865744028]
  Point clouds are popular representation for 3D shapes, but encode a particular sampling without accounting for shape priors or non-local information. We present PointGMM, a neural network that learns to generate hGMMs which are characteristic of the shape class. We show that as a generative model, PointGMM learns a meaningful latent space which enables generating consistents between existing shapes.
  arXiv  Detail & Related papers  (2020-03-30T10:34:59Z)

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.