mlsanityData to 7 Oct 2026

PointVector: A Vector Representation In Point Cloud Analysis

arXiv 2205.10528 ↗First posted 21 May 2022cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

In point cloud analysis, point-based methods have rapidly developed in recent years. These methods have recently focused on concise MLP structures, such as PointNeXt, which have demonstrated competitiveness with Convolutional and Transformer structures. However, standard MLPs are limited in their ability to extract local features effectively. To address this limitation, we propose a Vector-oriented Point Set Abstraction that can aggregate neighboring features through higher-dimensional vectors. To facilitate network optimization, we construct a transformation from scalar to vector using independent angles based on 3D vector rotations. Finally, we develop a PointVector model that follows the structure of PointNeXt. Our experimental results demonstrate that PointVector achieves state-of-the-art performance 72.3% mIOU on the S3DIS Area 5 and 78.4% mIOU on the S3DIS (6-fold cross-validation) with only 58% model parameters of PointNeXt. We hope our work will help the exploration of concise and effective feature representations. The code will be released soon.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 44 of its 63 references that are in the map. First posted on arXiv 21 May 2022.

Builds on

44 of 63 references.

References · 44

  1. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  5. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  6. 2020Point Transformercited by 1,462
  7. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  8. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  10. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  11. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  12. 2020PCT: Point cloud transformercited by 730
32 more
  1. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  2. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  3. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  4. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  5. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  6. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  7. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  8. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  9. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 284
  10. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  11. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  12. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  13. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 166
  14. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  15. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  16. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  17. 2020MVTN: Multi-View Transformation Network for 3D Shape Recognitioncited by 140
  18. 2021CycleMLP: A MLP-like Architecture for Dense Predictioncited by 126
  19. 2021AS-MLP: An Axial Shifted MLP Architecture for Visioncited by 101
  20. 2020A Closer Look at Local Aggregation Operators in Point Cloud Analysiscited by 87
  21. 2022Surface Representation for Point Cloudscited by 84
  22. 2019DeepGCNs: Making GCNs Go as Deep as CNNscited by 72
  23. 2021PointMixer: MLP-Mixer for Point Cloud Understandingcited by 71
  24. 2021An Image Patch is a Wave: Phase-Aware Vision MLPcited by 61
  25. 2021Adaptive Graph Convolution for Point Cloud Analysiscited by 60
  26. 2021PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysiscited by 58
  27. 2022Contrastive Boundary Learning for Point Cloud Segmentationcited by 56
  28. 2021PatchFormer: An Efficient Point Transformer with Patch Attentioncited by 43
  29. 2021ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learningcited by 29
  30. 2020SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Cloudscited by 27
  31. 2022Learning Local Displacements for Point Cloud Completioncited by 16
  32. 2020GeoConv: Geodesic Guided Convolution for Facial Action Unit Recognitioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 8; 2026: 6.

21 papers.

Sort:

By area:

  1. 2024PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learningcited by 21
  2. 2024KPConvX: Modernizing Kernel Point Convolution with Kernel Attentioncited by 16
  3. 2024X-3D: Explicit 3D Structure Modeling for Point Cloud Recognitioncited by 11
  4. 2025Spectral Informed Mamba for Robust Point Cloud Processingcited by 10
  5. 2024ConDense: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Imagescited by 9
  6. 2024Versatile Navigation under Partial Observability via Value-guided Diffusion Policycited by 5
  7. 2025Fourier Decomposition for Explicit Representation of 3D Point Cloud Attributescited by 4
  8. 2025PointDiffuse: A Dual-Conditional Diffusion Model for Enhanced Point Cloud Semantic Segmentationcited by 2
  9. 2025EDBench: Large-Scale Electron Density Data for Molecular Modelingcited by 2
  10. 2024OpenTrench3D: A Photogrammetric 3D Point Cloud Dataset for Semantic Segmentation of Underground Utilitiescited by 1
  11. 2025SUM Parts: Benchmarking Part-Level Semantic Segmentation of Urban Meshescited by 1
  12. 2025Enhancing point cloud analysis via neighbor aggregation correction based on cross-stage structure correlationcited by 1
9 more
  1. 2025FastPoint: Accelerating 3D Point Cloud Model Inference via Sample Point Distance Predictioncited by 1
  2. 2026ED-DiT: Physics-Guided Diffusion Pretraining for Transferable Molecular Representations from Electron Densitycited by 1
  3. 2024Soft Masked Transformer for Point Cloud Processing with Skip Attention-Based Upsamplingcited by 0
  4. 2025FractalCloud: A Fractal-Inspired Architecture for Efficient Large-Scale Point Cloud Processingcited by 0
  5. 2026Efficient Point Cloud Processing with High-Dimensional Positional Encoding and Non-Local MLPscited by 0
  6. 2026Channel-Level Relation to Attentive Aggregation with Neighborhood-Homogeneity Constraint for Point Cloud Analysiscited by 0
  7. 2026RadiusFPS: Efficient Farthest Point Sampling on CPUs and GPUs via Spherical Voxel Pruningcited by 0
  8. 2026PointCHR: Point Cloud Analysis via Curvature-Aware Hyperbolic Rectificationcited by 0
  9. 2026GAPrompt++: Multi-Granular Geometry-Aware Point Cloud Prompt for 3D Vision Modelcited by 0