mlsanityData to 7 Oct 2026

Relation-Shape Convolutional Neural Network for Point Cloud Analysis

arXiv 1904.07601 ↗First posted 16 Apr 2019cs.CV cs.AI cs.CGcited by 346

Not on the map. Why?

Abstract (arXiv)

Point cloud analysis is very challenging, as the shape implied in irregular points is difficult to capture. In this paper, we propose RS-CNN, namely, Relation-Shape Convolutional Neural Network, which extends regular grid CNN to irregular configuration for point cloud analysis. The key to RS-CNN is learning from relation, i.e., the geometric topology constraint among points. Specifically, the convolutional weight for local point set is forced to learn a high-level relation expression from predefined geometric priors, between a sampled point from this point set and the others. In this way, an inductive local representation with explicit reasoning about the spatial layout of points can be obtained, which leads to much shape awareness and robustness. With this convolution as a basic operator, RS-CNN, a hierarchical architecture can be developed to achieve contextual shape-aware learning for point cloud analysis. Extensive experiments on challenging benchmarks across three tasks verify RS-CNN achieves the state of the arts.

Key facts. Cited by 346 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 80; 2022: 99; 2023: 69; 2024: 53; 2025: 29; 2026: 16.

346 papers.

Sort:

By area:

  1. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  2. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  3. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  4. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
  5. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  6. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  7. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 284
  8. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 263
  9. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 262
  10. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  11. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  12. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 197
38 more
  1. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  2. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 166
  3. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  4. 2023Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretrainingcited by 162
  5. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 157
  6. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  7. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  8. 2022Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoderscited by 143
  9. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  10. 2024ShapeLLM: Universal 3D Object Understanding for Embodied Interactioncited by 133
  11. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  12. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
  13. 2023DSVT: Dynamic Sparse Voxel Transformer with Rotated Setscited by 122
  14. 2022Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?cited by 121
  15. 2022PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Modelscited by 117
  16. 2023PointGPT: Auto-regressively Generative Pre-training from Point Cloudscited by 115
  17. 2021Beyond Self-attention: External Attention using Two Linear Layers for Visual Taskscited by 109
  18. 2021Fast Point Transformercited by 103
  19. 2022POCO: Point Convolution for Surface Reconstructioncited by 91
  20. 2021Generative Models as Distributions of Functionscited by 89
  21. 2022Surface Representation for Point Cloudscited by 84
  22. 2022Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptionscited by 78
  23. 2023UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representationcited by 74
  24. 2021Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusioncited by 71
  25. 2021PointMixer: MLP-Mixer for Point Cloud Understandingcited by 71
  26. 2024Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategycited by 71
  27. 2022Benchmarking and Analyzing Point Cloud Classification under Corruptionscited by 70
  28. 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
  29. 2023Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Modelscited by 67
  30. 2024Point Cloud Mamba: Point Cloud Learning via State Space Modelcited by 66
  31. 2023AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformerscited by 65
  32. 2021Adaptive Graph Convolution for Point Cloud Analysiscited by 60
  33. 2021Regularization Strategy for Point Cloud via Rigidly Mixed Samplecited by 59
  34. 2021PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysiscited by 58
  35. 2021Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Cloudscited by 55
  36. 2022Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Surveycited by 54
  37. 2021Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learningcited by 52
  38. 2023Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-trainingcited by 52

50 most cited of 346 All 346 (JSON)