mlsanityData to 7 Oct 2026

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

arXiv 1706.02413 ↗First posted 7 Jun 2017cs.CVcited by 4,384

On the map: World models → World modeling from LiDAR generation

Abstract (arXiv)

Few prior works study deep learning on point sets. PointNet by Qi et al. is a pioneer in this direction. However, by design PointNet does not capture local structures induced by the metric space points live in, limiting its ability to recognize fine-grained patterns and generalizability to complex scenes. In this work, we introduce a hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set. By exploiting metric space distances, our network is able to learn local features with increasing contextual scales. With further observation that point sets are usually sampled with varying densities, which results in greatly decreased performance for networks trained on uniform densities, we propose novel set learning layers to adaptively combine features from multiple scales. Experiments show that our network called PointNet++ is able to learn deep point set features efficiently and robustly. In particular, results significantly better than state-of-the-art have been obtained on challenging benchmarks of 3D point clouds.

Key facts. Cited by 4,384 papers in the map (data through 7 Oct 2026). Placed in World modeling from LiDAR generation, one of 11 directions in World models. Builds on 1 of its 33 references that are in the map. First posted on arXiv 7 Jun 2017.

Builds on

1 of 33 references.

Closest ancestors · 1

Same direction, newest first

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation2 Dec

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 637; 2022: 751; 2023: 863; 2024: 807; 2025: 793; 2026: 532.

4,384 papers.

Sort:

By area:

  1. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
  2. 2021Perceiver: General Perception with Iterative Attentioncited by 1,089
  3. 2021Transformers in Vision: A Surveycited by 1,009
  4. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 844
  5. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
  6. 2024Structured 3D Latents for Scalable and Versatile 3D Generationcited by 742
  7. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  8. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  9. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  10. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  11. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 584
  12. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
38 more
  1. 2021KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3Dcited by 570
  2. 2022OpenScene: 3D Scene Understanding with Open Vocabulariescited by 556
  3. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  4. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  5. 2023Ferret: Refer and Ground Anything Anywhere at Any Granularitycited by 498
  6. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  7. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  8. 20233DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Modelscited by 449
  9. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
  10. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 442
  11. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  12. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
  13. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  14. 2023An Embodied Generalist Agent in 3D Worldcited by 355
  15. 2021ScanQA: 3D Question Answering for Spatial Scene Understandingcited by 340
  16. 2022BEVFusion: A Simple and Robust LiDAR-Camera Fusion Frameworkcited by 334
  17. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  18. 2023Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Drivingcited by 325
  19. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 324
  20. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  21. 2022Mask3D: Mask Transformer for 3D Semantic Instance Segmentationcited by 299
  22. 2023OpenMask3D: Open-Vocabulary 3D Instance Segmentationcited by 288
  23. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 284
  24. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 274
  25. 2021DeepCAD: A Deep Generative Network for Computer-Aided Design Modelscited by 266
  26. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 263
  27. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 262
  28. 2021Voxel Transformer for 3D Object Detectioncited by 247
  29. 2022Language-Grounded Indoor 3D Semantic Segmentation in the Wildcited by 243
  30. 2023Diffusion-based Generation, Optimization, and Planning in 3D Scenescited by 237
  31. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  32. 2023Uni3D: Exploring Unified 3D Representation at Scalecited by 231
  33. 2023Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representationcited by 225
  34. 2022DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detectioncited by 224
  35. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  36. 2023MVImgNet: A Large-scale Dataset of Multi-view Imagescited by 219
  37. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  38. 2021Group-Free 3D Object Detection via Transformerscited by 215

50 most cited of 4,384 All 4,384 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Point-MoE: Large-Scale Multi-Dataset Training with Mixture-of-Experts for 3D Semantic Segmentation
  2. 2018Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds using Convolutional Neural Networks
  3. 2026Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds
  4. 2025Few to Big: Prototype Expansion Network via Diffusion Learner for Point Cloud Few-shot Semantic Segmentation
  5. 2026Deformation-based In-Context Learning for Point Cloud Understanding
  6. 2024PointInfinity: Resolution-Invariant Point Diffusion Models
  7. 2025PointDGRWKV: Generalizing RWKV-like Architecture to Unseen Domains for Point Cloud Classification
  8. 2026Learning Point Cloud Geometry as a Statistical Manifold: Theory and Practice ↗