mlsanityData to 13 Oct 2026

Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategy

arXiv 2403.06467 ↗First posted 11 Mar 2024cs.CVcited by 71

On the map: State-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing

Abstract (arXiv)

Recently, state space model (SSM) has gained great attention due to its promising performance, linear complexity, and long sequence modeling ability in both language and image domains. However, it is non-trivial to extend SSM to the point cloud field, because of the causality requirement of SSM and the disorder and irregularity nature of point clouds. In this paper, we propose a novel SSM-based point cloud processing backbone, named Point Mamba, with a causality-aware ordering mechanism. To construct the causal dependency relationship, we design an octree-based ordering strategy on raw irregular points, globally sorting points in a z-order sequence and also retaining their spatial proximity. Our method achieves state-of-the-art performance compared with transformer-based counterparts, with 93.4% accuracy and 75.7 mIOU respectively on the ModelNet40 classification dataset and ScanNet semantic segmentation dataset. Furthermore, our Point Mamba has linear complexity, which is more efficient than transformer-based methods. Our method demonstrates the great potential that SSM can serve as a generic backbone in point cloud understanding. Codes are released at https://github.com/IRMVLab/Point-Mamba.

Key facts. Cited by 71 papers in the map (data through 13 Oct 2026). Placed in Point clouds, detection and remote sensing, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 49 of its 61 references that are in the map. First posted on arXiv 11 Mar 2024.

Builds on

49 of 61 references.

References · 49

  1. 2017Attention Is All You Needcited by 60,106
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,111
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,231
  5. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,658
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,389
  7. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,096
  8. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,440
  9. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,222
  10. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,475
  11. 2020Point Transformercited by 1,465
  12. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,205
37 more
  1. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,055
  2. 2024VMamba: Visual State Space Modelcited by 963
  3. 2022Simplified State Space Layers for Sequence Modelingcited by 781
  4. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  5. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 750
  6. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 747
  7. 2020PCT: Point cloud transformercited by 731
  8. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 722
  9. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  10. 2019Panoptic Feature Pyramid Networkscited by 644
  11. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 607
  12. 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 602
  13. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  14. 2023Point Transformer V3: Simpler, Faster, Strongercited by 584
  15. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  16. 2022On the Parameterization and Initialization of Diagonal State Space Modelscited by 420
  17. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 385
  18. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  19. 2022Diagonal State Spaces are as Effective as Structured State Spacescited by 350
  20. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  21. 2020Visual Transformers: Token-based Image Representation and Processing for Computer Visioncited by 334
  22. 2022Long Range Language Modeling via Gated State Spacescited by 265
  23. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  24. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  25. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  26. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  27. 2022Mega: Moving Average Equipped Gated Attentioncited by 178
  28. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  29. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  30. 2022Liquid Structural State-Space Modelscited by 134
  31. 2023Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understandingcited by 111
  32. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 107
  33. 2021Fast Point Transformercited by 103
  34. 2018Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Networkcited by 100
  35. 2022SWFormer: Sparse Window Transformer for 3D Object Detection in Point Cloudscited by 92
  36. 2022ToolFlowNet: Robotic Manipulation with Tools via Predicting Tool Flow from Point Cloudscited by 54
  37. 2019A Unified Point-Based Framework for 3D Segmentationcited by 33

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 36; 2025: 24; 2026: 11.

71 papers.

Sort:

By area:

  1. 2026GigaWorld-Policy: An Efficient Action-Centered World--Action Modelcited by 133
  2. 2024State Space Model for New-Generation Network Alternative to Transformers: A Surveycited by 59
  3. 2024Vision Mamba: A Comprehensive Survey and Taxonomycited by 53
  4. 2024A Survey on Visual Mambacited by 50
  5. 2024DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenescited by 45
  6. 2024Visual Mamba: A Survey and New Outlookscited by 41
  7. 2024DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusioncited by 38
  8. 2024SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentationcited by 31
  9. 2024NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoisingcited by 29
  10. 2024OccMamba: Semantic Occupancy Prediction with State Space Modelscited by 29
  11. 2024Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networkscited by 26
  12. 2024Mamba-FETrack: Frame-Event Tracking via State Space Modelcited by 22
38 more
  1. 2024PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learningcited by 21
  2. 2024Mambular: A Sequential Model for Tabular Deep Learningcited by 19
  3. 2024Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and Regression: EventMambacited by 18
  4. 2024Mamba in Vision: A Comprehensive Survey of Techniques and Applicationscited by 18
  5. 2024QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Modelcited by 18
  6. 2024MARCA: Mamba Accelerator with ReConfigurable Architecturecited by 13
  7. 2024MambaMOS: LiDAR-based 3D Moving Object Segmentation with Motion-aware State Space Modelcited by 12
  8. 2024MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Modelscited by 11
  9. 2024Multi-Modal UAV Detection, Classification and Tracking Algorithm -- Technical Report for CVPR 2024 UG2 Challengecited by 9
  10. 2024A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervisioncited by 9
  11. 2025Skip Mamba Diffusion for Monocular 3D Semantic Scene Completioncited by 9
  12. 2024QMamba: On First Exploration of Vision Mamba for Image Quality Assessmentcited by 8
  13. 2024Vision Mamba for Classification of Breast Ultrasound Imagescited by 7
  14. 2024MUSE: Mamba is Efficient Multi-scale Learner for Text-video Retrievalcited by 7
  15. 2024MambaPlace:Text-to-Point-Cloud Cross-Modal Place Recognition with Attention Mamba Mechanismscited by 7
  16. 2024On the Efficiency of NLP-Inspired Methods for Tabular Deep Learningcited by 7
  17. 2025TopoLiDM: Topology-Aware LiDAR Diffusion Models for Interpretable and Realistic LiDAR Point Cloud Generationcited by 6
  18. 2024Millimeter Wave Radar-based Human Activity Recognition for Healthcare Monitoring Robotcited by 5
  19. 2024Faster Vision Mamba is Rebuilt in Minutes via Merged Token Re-trainingcited by 5
  20. 2024FlowMamba: Learning Point Cloud Scene Flow with Global Motion Propagationcited by 5
  21. 2026Nexus: Native Mesh Generation with Diffusioncited by 5
  22. 2024LaMamba-Diff: Linear-Time High-Fidelity Diffusion Models Based on Local Attention and Mambacited by 4
  23. 2024Monocular Visual Place Recognition in LiDAR Maps via Cross-Modal State Space Model and Multi-View Matchingcited by 4
  24. 2024START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformationcited by 4
  25. 2025Beyond Frame-wise Tracking: A Trajectory-based Paradigm for Efficient Point Cloud Trackingcited by 4
  26. 20254DSTR: Advancing Generative 4D Gaussians with Spatial-Temporal Rectification for High-Quality and Consistent 4D Generationcited by 4
  27. 2024NIMBA: Towards Robust and Principled Processing of Point Clouds With SSMscited by 3
  28. 2025Efficient Spiking Point Mamba for Point Cloud Analysiscited by 3
  29. 2025CymbaDiff: Structured Spatial Diffusion for Sketch-based 3D Semantic Urban Scene Generationcited by 3
  30. 2025IEC3D-AD: A 3D Dataset of Industrial Equipment Components for Unsupervised Point Cloud Anomaly Detectioncited by 3
  31. 2025CloudMamba: Grouped Selective State Spaces for Point Cloud Analysiscited by 3
  32. 2026Mamba-CAD: State Space Model For 3D Computer-Aided Design Generative Modelingcited by 3
  33. 2025Global-Aware Monocular Semantic Scene Completion with State Space Modelscited by 2
  34. 2025Hierarchical Feature Learning for Medical Point Clouds via State Space Modelcited by 2
  35. 2025InterMamba: Efficient Human-Human Interaction Generation with Adaptive Spatio-Temporal Mambacited by 2
  36. 2025MeshMamba: State Space Models for Articulated 3D Mesh Generation and Reconstructioncited by 2
  37. 2025HydraMamba: Multi-Head State Space Model for Global Point Cloud Learningcited by 2
  38. 2025EgoMusic-driven Human Dance Motion Estimation with Skeleton Mambacited by 2

50 most cited of 71 All 71 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Point Cloud Mamba: Point Cloud Learning via State Space Model
  2. 2024PointMamba: A Simple State Space Model for Point Cloud Analysis
  3. 2024Pamba: Enhancing Global Interaction in Point Clouds via State Space Model
  4. 2024PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysis
  5. 2024PointABM:Integrating Bidirectional State Space Model with Multi-Head Self-Attention for Point Cloud Analysis
  6. 2025ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding
  7. 2025StruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning
  8. 2024Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model