mlsanityData to 14 Oct 2026

Dynamic Graph CNN for Learning on Point Clouds

arXiv 1801.07829 ↗First posted 24 Jan 2018cs.CVcited by 2,223

Not on the map. Why?

Cited by 53 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices. While hand-designed features on point clouds have long been proposed in graphics and vision, however, the recent overwhelming success of convolutional neural networks (CNNs) for image analysis suggests the value of adapting insight from CNN to the point cloud world. Point clouds inherently lack topological information so designing a model to recover topology can enrich the representation power of point clouds. To this end, we propose a new neural network module dubbed EdgeConv suitable for CNN-based high-level tasks on point clouds including classification and segmentation. EdgeConv acts on graphs dynamically computed in each layer of the network. It is differentiable and can be plugged into existing architectures. Compared to existing modules operating in extrinsic space or treating each point independently, EdgeConv has several appealing properties: It incorporates local neighborhood information; it can be stacked applied to learn global shape properties; and in multi-layer systems affinity in feature space captures semantic characteristics over potentially long distances in the original embedding. We show the performance of our model on standard benchmarks including ModelNet40, ShapeNetPart, and S3DIS.

Key facts. Cited by 2,223 papers in the map (data through 14 Oct 2026). First posted on arXiv 24 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 372; 2022: 462; 2023: 437; 2024: 399; 2025: 332; 2026: 221.

2,223 papers.

Sort:

By area:

  1. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  2. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  3. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 553
  4. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  5. 2023Ferret: Refer and Ground Anything Anywhere at Any Granularitycited by 509
  6. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 478
  7. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 463
  8. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  9. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 458
  10. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 436
  11. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 388
  12. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
38 more
  1. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  2. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 326
  3. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 305
  4. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 286
  5. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 267
  6. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 264
  7. 2023MeshGPT: Generating Triangle Meshes with Decoder-Only Transformerscited by 259
  8. 2023Uni3D: Exploring Unified 3D Representation at Scalecited by 237
  9. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  10. 2023MVImgNet: A Large-scale Dataset of Multi-view Imagescited by 220
  11. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  12. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  13. 2023NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classificationcited by 210
  14. 2023DepGraph: Towards Any Structural Pruningcited by 203
  15. 2022SoftGroup for 3D Instance Segmentation on Point Cloudscited by 200
  16. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  17. 2022FUTR3D: A Unified Sensor Fusion Framework for 3D Detectioncited by 194
  18. 2021Shape As Points: A Differentiable Poisson Solvercited by 187
  19. 2022PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learningcited by 187
  20. 2022Vision GNN: An Image is Worth Graph of Nodescited by 186
  21. 2023OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understandingcited by 184
  22. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  23. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
  24. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  25. 2021Training Graph Neural Networks with 1000 Layerscited by 169
  26. 2021Spherical Message Passing for 3D Graph Networkscited by 168
  27. 2021Frame Averaging for Invariant and Equivariant Network Designcited by 168
  28. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 167
  29. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 167
  30. 2023DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesiscited by 166
  31. 2023Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretrainingcited by 164
  32. 2022CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-trainingcited by 160
  33. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 158
  34. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  35. 2021CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registrationcited by 152
  36. 2022Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Modelscited by 151
  37. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  38. 2022Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoderscited by 144

50 most cited of 2,223 All 2,223 (JSON)