DeepGMR: Learning Latent Gaussian Mixture Models for Registration

• URL: http://arxiv.org/abs/2008.09088v1
• Date: Thu, 20 Aug 2020 17:25:16 GMT
• Title: DeepGMR: Learning Latent Gaussian Mixture Models for Registration
• Authors: Wentao Yuan, Ben Eckart, Kihwan Kim, Varun Jampani, Dieter Fox, Jan Kautz
• Abstract summary: 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.
• Score: 113.74060941036664
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Point cloud registration is a fundamental problem in 3D computer vision, graphics and robotics. For the last few decades, existing registration algorithms have struggled in situations with large transformations, noise, and time constraints. In this paper, we introduce Deep Gaussian Mixture Registration (DeepGMR), the first learning-based registration method that explicitly leverages a probabilistic registration paradigm by formulating registration as the minimization of KL-divergence between two probability distributions modeled as mixtures of Gaussians. We design a neural network that extracts pose-invariant correspondences between raw point clouds and Gaussian Mixture Model (GMM) parameters and two differentiable compute blocks that recover the optimal transformation from matched GMM parameters. This construction allows the network learn an SE(3)-invariant feature space, producing a global registration method that is real-time, generalizable, and robust to noise. Across synthetic and real-world data, our proposed method shows favorable performance when compared with state-of-the-art geometry-based and learning-based registration methods.

Related papers

• Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration [2.814748676983944]
  We propose a graph neural network model embedded with a local Spherical Euclidean 3D equivariance property through SE(3) message passing based propagation. Our model is composed mainly of a descriptor module, equivariant graph layers, match similarity, and the final regression layers. Experiments conducted on the 3DMatch and KITTI datasets exhibit the compelling and robust performance of our model compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-10-08T06:48:01Z)
• Cramer Type Distances for Learning Gaussian Mixture Models by Gradient Descent [0.0]
  As of today, few known algorithms can fit or learn Gaussian mixture models. We propose a distance function called Sliced Cram'er 2-distance for learning general multivariate GMMs. These features are especially useful for distributional reinforcement learning and Deep Q Networks.
  arXiv  Detail & Related papers  (2023-07-13T13:43:02Z)
• GSMorph: Gradient Surgery for cine-MRI Cardiac Deformable Registration [62.41725951450803]
  Learning-based deformable registration relies on weighted objective functions trading off registration accuracy and smoothness of the field. We construct a registration model based on the gradient surgery mechanism, named GSMorph, to achieve a hyper parameter-free balance on multiple losses. Our method is model-agnostic and can be merged into any deep registration network without introducing extra parameters or slowing down inference.
  arXiv  Detail & Related papers  (2023-06-26T13:32:09Z)
• 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)
• Deep Hough Voting for Robust Global Registration [52.40611370293272]
  We present an efficient framework for pairwise registration of real-world 3D scans, leveraging Hough voting in the 6D transformation parameter space. Our method outperforms state-of-the-art methods on 3DMatch and 3DLoMatch benchmarks while achieving comparable performance on KITTI odometry dataset.
  arXiv  Detail & Related papers  (2021-09-09T14:38:06Z)
• Correspondence-Free Point Cloud Registration with SO(3)-Equivariant Implicit Shape Representations [12.343333815270402]
  The proposed shape registration method achieves three major advantages through combining equivariant feature learning with implicit shape models. Results show superior performance compared with existing correspondence-free deep registration methods.
  arXiv  Detail & Related papers  (2021-07-21T18:18:21Z)
• Canny-VO: Visual Odometry with RGB-D Cameras based on Geometric 3D-2D Edge Alignment [85.32080531133799]
  This paper reviews the classical problem of free-form curve registration and applies it to an efficient RGBD visual odometry system called Canny-VO. Two replacements for the distance transformation commonly used in edge registration are proposed: Approximate Nearest Neighbour Fields and Oriented Nearest Neighbour Fields. 3D2D edge alignment benefits from these alternative formulations in terms of both efficiency and accuracy.
  arXiv  Detail & Related papers  (2020-12-15T11:42:17Z)
• Effective multi-view registration of point sets based on student's t mixture model [15.441928157356477]
  This paper proposes an effective registration method based on Student's t Mixture Model (StMM) It is more efficient to achieve multi-view registration since all t-distribution centroids can be obtained by the NN search method. Experimental results illustrate its superior performance and accuracy over state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-12-13T08:27:29Z)
• 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.