kNN-Res: Residual Neural Network with kNN-Graph coherence for point cloud registration

• URL: http://arxiv.org/abs/2304.00050v3
• Date: Wed, 27 Nov 2024 12:22:50 GMT
• Title: kNN-Res: Residual Neural Network with kNN-Graph coherence for point cloud registration
• Authors: Muhammad S. Battikh, Artem Lensky, Dillon Hammill, Matthew Cook,
• Abstract summary: We present a method based on a residual neural network for point set registration. The proposed regularization relies on a global smoothness constraint as a proxy for preserving local topology. We present a theoretical justification for our Jacobian-based cost showing that it is sufficient for the coherence kNN-graph of the transformed point set.
• Score: 0.464982780843177
• License:
• Abstract: In this paper, we present a method based on a residual neural network for point set registration that preserves the topological structure of the target point set. Similar to coherent point drift (CPD), the registration (alignment) problem is viewed as the movement of data points sampled from a target distribution along a regularized displacement vector field. Although the coherence constraint in CPD is stated in terms of local motion coherence, the proposed regularization relies on a global smoothness constraint as a proxy for preserving local topology. This makes CPD less flexible when the deformation is locally rigid but globally non-rigid as in the case of multiple objects and articulate pose registration. A kNN-graph coherence cost and geometric-aware statistical distances are proposed to mitigate these issues. To create an end-to-end trainable pipeline, a simple Jacobian-based cost is introduced as a proxy for the intrinsically discrete kNN-graph cost. We present a theoretical justification for our Jacobian-based cost showing that it is sufficient for the preservation of the kNN-graph of the transformed point set. Further, to tackle the registration of high-dimensional point sets, a constant time stochastic approximation of the kNN-graph coherence cost is introduced. The proposed method is illustrated on several 2-dimensional examples and tested on high-dimensional flow cytometry datasets where the task is to align two distributions of cells whilst preserving the kNN-graph in order to preserve the biological signal of the transformed data. The implementation of the proposed approach is available at https://github.com/MuhammadSaeedBatikh/kNN-Res_Demo/ under the MIT license.

Related papers

• Positional Encoder Graph Quantile Neural Networks for Geographic Data [4.277516034244117]
  We introduce the Positional Graph Quantile Neural Network (PE-GQNN), a novel method that integrates PE-GNNs, Quantile Neural Networks, and recalibration techniques in a fully nonparametric framework. Experiments on benchmark datasets demonstrate that PE-GQNN significantly outperforms existing state-of-the-art methods in both predictive accuracy and uncertainty quantification.
  arXiv  Detail & Related papers  (2024-09-27T16:02:12Z)
• SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid Registration [76.40993825836222]
  We propose SPARE, a novel formulation that utilizes a symmetrized point-to-plane distance for robust non-rigid registration. The proposed method greatly improves the accuracy of non-rigid registration problems and maintains relatively high solution efficiency.
  arXiv  Detail & Related papers  (2024-05-30T15:55:04Z)
• Deep Manifold Graph Auto-Encoder for Attributed Graph Embedding [51.75091298017941]
  This paper proposes a novel Deep Manifold (Variational) Graph Auto-Encoder (DMVGAE/DMGAE) for attributed graph data. The proposed method surpasses state-of-the-art baseline algorithms by a significant margin on different downstream tasks across popular datasets.
  arXiv  Detail & Related papers  (2024-01-12T17:57:07Z)
• Shape-Graph Matching Network (SGM-net): Registration for Statistical Shape Analysis [20.58923754314197]
  This paper focuses on the statistical analysis of shapes of data objects called shape graphs. A critical need here is a constrained registration of points (nodes to nodes, edges to edges) across objects. This paper tackles this registration problem using a novel neural-network architecture.
  arXiv  Detail & Related papers  (2023-08-14T00:42:03Z)
• SEM-GAT: Explainable Semantic Pose Estimation using Learned Graph Attention [10.883346969896621]
  This paper proposes a Graph Neural Network(GNN)-based method for exploiting semantics and local geometry to guide the identification of reliable pointcloud registration candidates. Semantic and morphological features of the environment serve as key reference points for registration, enabling accurate lidar-based pose estimation. We test our method on the KITTI odometry dataset, achieving competitive accuracy compared to benchmark methods and a higher track smoothness while relying on significantly fewer network parameters.
  arXiv  Detail & Related papers  (2023-08-07T16:43:46Z)
• Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network [59.79008107609297]
  We propose in this paper to approximate the joint posterior over the structure of a Bayesian Network. We use a single GFlowNet whose sampling policy follows a two-phase process. Since the parameters are included in the posterior distribution, this leaves more flexibility for the local probability models.
  arXiv  Detail & Related papers  (2023-05-30T19:16:44Z)
• Neural networks for geospatial data [0.0]
  NN-GLS is a new neural network estimation algorithm for the non-linear mean in GP models. We show that NN-GLS admits a representation as a special type of graph neural network (GNN) Theoretically, we show that NN-GLS will be consistent for irregularly observed spatially correlated data processes.
  arXiv  Detail & Related papers  (2023-04-18T17:52:23Z)
• On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias [50.84569563188485]
  We show that gradient flow converges in direction when labels are determined by the sign of a target network with $r$ neurons. Our result may already hold for mild over- parameterization, where the width is $tildemathcalO(r)$ and independent of the sample size.
  arXiv  Detail & Related papers  (2022-05-18T16:57:10Z)
• A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries [62.28265459308354]
  Network learns end-to-end mapping between spatial positions and CFD quantities. Incompress laminar steady flow past a cylinder with various shapes for its cross section is considered. Network predicts the flow fields hundreds of times faster than our conventional CFD.
  arXiv  Detail & Related papers  (2020-10-15T12:15:02Z)
• Scope Head for Accurate Localization in Object Detection [135.9979405835606]
  We propose a novel detector coined as ScopeNet, which models anchors of each location as a mutually dependent relationship. With our concise and effective design, the proposed ScopeNet achieves state-of-the-art results on COCO.
  arXiv  Detail & Related papers  (2020-05-11T04:00:09Z)

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.