mlsanityData to 14 Oct 2026

PointCNN: Convolution On X-Transformed Points

arXiv 1801.07791 ↗First posted 23 Jan 2018cs.CV cs.AI cs.GRcited by 764

Not on the map. Why?

Abstract (arXiv)

We present a simple and general framework for feature learning from point clouds. The key to the success of CNNs is the convolution operator that is capable of leveraging spatially-local correlation in data represented densely in grids (e.g. images). However, point clouds are irregular and unordered, thus directly convolving kernels against features associated with the points, will result in desertion of shape information and variance to point ordering. To address these problems, we propose to learn an X-transformation from the input points, to simultaneously promote two causes. The first is the weighting of the input features associated with the points, and the second is the permutation of the points into a latent and potentially canonical order. Element-wise product and sum operations of the typical convolution operator are subsequently applied on the X-transformed features. The proposed method is a generalization of typical CNNs to feature learning from point clouds, thus we call it PointCNN. Experiments show that PointCNN achieves on par or better performance than state-of-the-art methods on multiple challenging benchmark datasets and tasks.

Key facts. Cited by 764 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 161; 2022: 184; 2023: 156; 2024: 123; 2025: 90; 2026: 50.

764 papers.

Sort:

By area:

  1. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  2. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  3. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  4. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 463
  5. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  6. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 436
  7. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 388
  8. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  9. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  10. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 305
  11. 2023Geometry-Informed Neural Operator for Large-Scale 3D PDEscited by 303
  12. 2023OpenMask3D: Open-Vocabulary 3D Instance Segmentationcited by 289
38 more
  1. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 267
  2. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 264
  3. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  4. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  5. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  6. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 200
  7. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  8. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  9. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  10. 2021The Values Encoded in Machine Learning Researchcited by 172
  11. 2021Frame Averaging for Invariant and Equivariant Network Designcited by 168
  12. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 167
  13. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 167
  14. 2023Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretrainingcited by 164
  15. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  16. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  17. 2022Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoderscited by 144
  18. 2022GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Partscited by 139
  19. 2023Meta-Transformer: A Unified Framework for Multimodal Learningcited by 136
  20. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  21. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  22. 2022Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?cited by 122
  23. 2023PointGPT: Auto-regressively Generative Pre-training from Point Cloudscited by 115
  24. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 110
  25. 2021Beyond Self-attention: External Attention using Two Linear Layers for Visual Taskscited by 109
  26. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 109
  27. 20213D Object Detection for Autonomous Driving: A Surveycited by 106
  28. 2024SAMPart3D: Segment Any Part in 3D Objectscited by 97
  29. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
  30. 2022Learning to Generate Realistic LiDAR Point Cloudscited by 93
  31. 2022POCO: Point Convolution for Surface Reconstructioncited by 92
  32. 2021Neural Scene Flow Priorcited by 91
  33. 2023SAI3D: Segment Any Instance in 3D Scenescited by 90
  34. 2021Generative Models as Distributions of Functionscited by 89
  35. 2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
  36. 2023HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splattingcited by 89
  37. 2023Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Trainingcited by 86
  38. 2022Surface Representation for Point Cloudscited by 84

50 most cited of 764 All 764 (JSON)