mlsanityData to 7 Oct 2026

RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds

arXiv 1911.11236 ↗First posted 25 Nov 2019cs.CV cs.LG eess.IVcited by 584

Not on the map. Why?

Abstract (arXiv)

We study the problem of efficient semantic segmentation for large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing steps, most existing approaches are only able to be trained and operate over small-scale point clouds. In this paper, we introduce RandLA-Net, an efficient and lightweight neural architecture to directly infer per-point semantics for large-scale point clouds. The key to our approach is to use random point sampling instead of more complex point selection approaches. Although remarkably computation and memory efficient, random sampling can discard key features by chance. To overcome this, we introduce a novel local feature aggregation module to progressively increase the receptive field for each 3D point, thereby effectively preserving geometric details. Extensive experiments show that our RandLA-Net can process 1 million points in a single pass with up to 200X faster than existing approaches. Moreover, our RandLA-Net clearly surpasses state-of-the-art approaches for semantic segmentation on two large-scale benchmarks Semantic3D and SemanticKITTI.

Key facts. Cited by 584 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 104; 2022: 126; 2023: 135; 2024: 79; 2025: 84; 2026: 56.

584 papers.

Sort:

By area:

  1. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
  2. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  3. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
  4. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  5. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  6. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 306
  7. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 262
  8. 2022Language-Grounded Indoor 3D Semantic Segmentation in the Wildcited by 243
  9. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  10. 2024Mini-Splatting: Representing Scenes with a Constrained Number of Gaussianscited by 208
  11. 2023ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understandingcited by 199
  12. 2021RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentationcited by 173
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. 2021Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Trackingcited by 165
  4. 2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
  5. 20222DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Cloudscited by 157
  6. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
  7. 2021InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referringcited by 140
  8. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  9. 2022Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Cloudscited by 131
  10. 2023Rethinking Range View Representation for LiDAR Segmentationcited by 126
  11. 2023Spherical Transformer for LiDAR-based 3D Recognitioncited by 124
  12. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  13. 2023Segment Any Point Cloud Sequences by Distilling Vision Foundation Modelscited by 123
  14. 2022Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipecited by 122
  15. 2021NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenescited by 119
  16. 2022Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentationcited by 118
  17. 2021CKConv: Continuous Kernel Convolution For Sequential Datacited by 117
  18. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 108
  19. 2021Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentationcited by 107
  20. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 105
  21. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
  22. 2022LaserMix for Semi-Supervised LiDAR Semantic Segmentationcited by 92
  23. 2022Learning to Generate Realistic LiDAR Point Cloudscited by 91
  24. 2023SAI3D: Segment Any Instance in 3D Scenescited by 90
  25. 2023Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Trainingcited by 85
  26. 2022Surface Representation for Point Cloudscited by 84
  27. 2023Virtual Sparse Convolution for Multimodal 3D Object Detectioncited by 81
  28. 2022You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstrationcited by 79
  29. 2021Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentationcited by 76
  30. 2023RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Drivingcited by 76
  31. 2023OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learningcited by 75
  32. 2022PolarMix: A General Data Augmentation Technique for LiDAR Point Cloudscited by 74
  33. 2023FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformercited by 72
  34. 2023SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Drivingcited by 72
  35. 2021Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusioncited by 71
  36. 2021PointMixer: MLP-Mixer for Point Cloud Understandingcited by 71
  37. 2024Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategycited by 71
  38. 2022DP-NeRF: Deblurred Neural Radiance Field with Physical Scene Priorscited by 70

50 most cited of 584 All 584 (JSON)