mlsanityData to 7 Oct 2026

CloudWalker: Random walks for 3D point cloud shape analysis

arXiv 2112.01050 ↗First posted 2 Dec 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Point clouds are gaining prominence as a method for representing 3D shapes, but their irregular structure poses a challenge for deep learning methods. In this paper we propose CloudWalker, a novel method for learning 3D shapes using random walks. Previous works attempt to adapt Convolutional Neural Networks (CNNs) or impose a grid or mesh structure to 3D point clouds. This work presents a different approach for representing and learning the shape from a given point set. The key idea is to impose structure on the point set by multiple random walks through the cloud for exploring different regions of the 3D object. Then we learn a per-point and per-walk representation and aggregate multiple walk predictions at inference. Our approach achieves state-of-the-art results for two 3D shape analysis tasks: classification and retrieval.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 36 of its 67 references that are in the map. First posted on arXiv 2 Dec 2021.

Builds on

36 of 67 references.

References · 36

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  5. 2020Point Transformercited by 1,462
  6. 2017Deep Setscited by 1,394
  7. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  8. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  9. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  10. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  11. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  12. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
24 more
  1. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  2. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  3. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  4. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  5. 20203D-FUTURE: 3D Furniture shape with TextUREcited by 306
  6. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  7. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  8. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  9. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  10. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  11. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
  12. 2018Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Networkcited by 100
  13. 2017PCPNET: Learning Local Shape Properties from Raw Point Cloudscited by 97
  14. 2016Learning shape correspondence with anisotropic convolutional neural networkscited by 95
  15. 2018MeshNet: Mesh Neural Network for 3D Shape Representationcited by 95
  16. 2020Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloudcited by 71
  17. 2019Octree guided CNN with Spherical Kernels for 3D Point Cloudscited by 50
  18. 2020Dense-Resolution Network for Point Cloud Classification and Segmentationcited by 45
  19. 2020DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squarescited by 43
  20. 2020Random Walks: A Review of Algorithms and Applicationscited by 38
  21. 2020MeshWalker: Deep Mesh Understanding by Random Walkscited by 32
  22. 2021Learning Inner-Group Relations on Point Cloudscited by 29
  23. 2020PCEDNet : A Lightweight Neural Network for Fast and Interactive Edge Detection in 3D Point Cloudscited by 15
  24. 2019Point Cloud Processing via Recurrent Set Encodingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 0; 2026: 1.

4 papers.

  1. 2024Fast and Simple Explainability for Point Cloud Networkscited by 6
  2. 2023PatchContrast: Self-Supervised Pre-training for 3D Object Detectioncited by 3
  3. 2023Robustifying Point Cloud Networks by Refocusingcited by 2
  4. 2026Random Walk on Point Clouds for Feature Detectioncited by 0