mlsanityData to 14 Oct 2026

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

arXiv 2112.11258 ↗First posted 21 Dec 2021cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 32 of its 47 references that are in the map. First posted on arXiv 21 Dec 2021.

Builds on

32 of 47 references.

References · 32

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  5. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  7. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  8. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 772
  9. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  10. 2017Dynamic Routing Between Capsulescited by 689
  11. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  12. 2018PCN: Point Completion Networkcited by 384
20 more
  1. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  2. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  3. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  4. 2018PU-Net: Point Cloud Upsampling Networkcited by 209
  5. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 206
  6. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 181
  7. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  8. 2019PRNet: Self-Supervised Learning for Partial-to-Partial Registrationcited by 146
  9. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  10. 2018PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptorscited by 141
  11. 20183D Point Capsule Networkscited by 106
  12. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  13. 2019Learning elementary structures for 3D shape generation and matchingcited by 98
  14. 2018Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Cloudscited by 62
  15. 2019DeepCaps: Going Deeper with Capsule Networkscited by 42
  16. 2019Quaternion Equivariant Capsule Networks for 3D Point Cloudscited by 41
  17. 2020Canonical Capsules: Self-Supervised Capsules in Canonical Posecited by 30
  18. 2019Point2SpatialCapsule: Aggregating Features and Spatial Relationships of Local Regions on Point Clouds using Spatial-aware Capsulescited by 14
  19. 20183DCapsule: Extending the Capsule Architecture to Classify 3D Point Cloudscited by 5
  20. 2018Spherical Convolutional Neural Network for 3D Point Cloudscited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentationcited by 14