PointCaps: Raw Point Cloud Processing using Capsule Networks with Euclidean Distance Routing

• URL: http://arxiv.org/abs/2112.11258v1
• Date: Tue, 21 Dec 2021 14:34:39 GMT
• Title: PointCaps: Raw Point Cloud Processing using Capsule Networks with Euclidean Distance Routing
• Authors: Dishanika Denipitiyage, Vinoj Jayasundara, Ranga Rodrigo, Chamira U. S. Edussooriya
• Abstract summary: Raw point cloud processing using capsule networks is widely adopted in classification, reconstruction, and segmentation. Most of the existing capsule based network approaches are computationally heavy and fail at representing the entire point cloud as a single capsule. We propose PointCaps, a novel convolutional capsule architecture with parameter sharing.
• Score: 2.916675178729016
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Raw point cloud processing using capsule networks is widely adopted in classification, reconstruction, and segmentation due to its ability to preserve spatial agreement of the input data. However, most of the existing capsule based network approaches are computationally heavy and fail at representing the entire point cloud as a single capsule. We address these limitations in existing capsule network based approaches by proposing PointCaps, a novel convolutional capsule architecture with parameter sharing. Along with PointCaps, we propose a novel Euclidean distance routing algorithm and a class-independent latent representation. The latent representation captures physically interpretable geometric parameters of the point cloud, with dynamic Euclidean routing, PointCaps well-represents the spatial (point-to-part) relationships of points. PointCaps has a significantly lower number of parameters and requires a significantly lower number of FLOPs while achieving better reconstruction with comparable classification and segmentation accuracy for raw point clouds compared to state-of-the-art capsule networks.

Related papers

• Fully-Geometric Cross-Attention for Point Cloud Registration [51.865371511201765]
  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.
  arXiv  Detail & Related papers  (2025-02-12T10:44:36Z)
• PointCFormer: a Relation-based Progressive Feature Extraction Network for Point Cloud Completion [19.503392612245474]
  Point cloud completion aims to reconstruct the complete 3D shape from incomplete point clouds. We introduce PointCFormer, a transformer framework optimized for robust global retention and precise local detail capture. PointCFormer demonstrates state-of-the-art performance on several widely used benchmarks.
  arXiv  Detail & Related papers  (2024-12-11T14:37:21Z)
• Implicit Neural Compression of Point Clouds [58.45774938982386]
  NeRC$textbf3$ is a novel point cloud compression framework leveraging implicit neural representations to handle both geometry and attributes. For dynamic point clouds, 4D-NeRC$textbf3$ demonstrates superior geometry compression compared to state-of-the-art G-PCC and V-PCC standards.
  arXiv  Detail & Related papers  (2024-12-11T03:22:00Z)
• Hierarchical Object-Centric Learning with Capsule Networks [0.0]
  Capsule networks (CapsNets) were introduced to address convolutional neural networks limitations. This thesis investigates the intriguing aspects of CapsNets and focuses on three key questions to unlock their full potential.
  arXiv  Detail & Related papers  (2024-05-30T09:10:33Z)
• Point Cloud Compression with Implicit Neural Representations: A Unified Framework [54.119415852585306]
  We present a pioneering point cloud compression framework capable of handling both geometry and attribute components. Our framework utilizes two coordinate-based neural networks to implicitly represent a voxelized point cloud. Our method exhibits high universality when contrasted with existing learning-based techniques.
  arXiv  Detail & Related papers  (2024-05-19T09:19:40Z)
• Parametric Surface Constrained Upsampler Network for Point Cloud [33.033469444588086]
  We introduce a novel surface regularizer into the upsampler network by forcing the neural network to learn the underlying parametric surface represented by bicubic functions and rotation functions. These designs are integrated into two different networks for two tasks that take advantages of upsampling layers. The state-of-the-art experimental results on both tasks demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2023-03-14T21:12:54Z)
• CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning [53.1436669083784]
  We propose a generic Contour-Perturbed Reconstruction Network (CP-Net), which can effectively guide self-supervised reconstruction to learn semantic content in the point cloud. For classification, we get a competitive result with the fully-supervised methods on ModelNet40 (92.5% accuracy) and ScanObjectNN (87.9% accuracy)
  arXiv  Detail & Related papers  (2022-01-20T15:04:12Z)
• PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery [35.353458457283544]
  Point Cloud Sampling and Recovery (PCSR) is critical for massive real-time point cloud collection and processing. We propose a novel Locally Invertible Embedding for point cloud adaptive sampling and recovery (PointLIE) PointLIE unifies point cloud sampling and upsampling to one single framework through bi-directional learning.
  arXiv  Detail & Related papers  (2021-04-30T05:55:59Z)
• Deformable Capsules for Object Detection [3.702343116848637]
  We introduce a new family of capsule networks, deformable capsules (textitDeformCaps), to address a very important problem in computer vision: object detection. We demonstrate that the proposed methods efficiently scale up to create the first-ever capsule network for object detection in the literature.
  arXiv  Detail & Related papers  (2021-04-11T15:36:30Z)
• PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths [54.459879603473034]
  We design a novel neural network, named PMP-Net, to mimic the behavior of an earth mover. It moves each point of the incomplete input to complete the point cloud, where the total distance of point moving paths should be shortest. It learns a strict and unique correspondence on point-level, which can capture the detailed topology and structure relationships between the incomplete shape and the complete target.
  arXiv  Detail & Related papers  (2020-12-07T01:34:38Z)
• SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification [93.54286830844134]
  We propose a method for 3D object completion and classification based on point clouds. For the decoder stage, we propose regional convolutions, a novel operator aimed at maximizing the global activation entropy. We evaluate our approach on different 3D tasks such as object completion and classification, achieving state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2020-08-17T14:32:35Z)

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.