mlsanityData to 13 Oct 2026

PointMamba: A Simple State Space Model for Point Cloud Analysis

arXiv 2402.10739 ↗First posted 16 Feb 2024cs.CVcited by 166

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

Abstract (arXiv)

Transformers have become one of the foundational architectures in point cloud analysis tasks due to their excellent global modeling ability. However, the attention mechanism has quadratic complexity, making the design of a linear complexity method with global modeling appealing. In this paper, we propose PointMamba, transferring the success of Mamba, a recent representative state space model (SSM), from NLP to point cloud analysis tasks. Unlike traditional Transformers, PointMamba employs a linear complexity algorithm, presenting global modeling capacity while significantly reducing computational costs. Specifically, our method leverages space-filling curves for effective point tokenization and adopts an extremely simple, non-hierarchical Mamba encoder as the backbone. Comprehensive evaluations demonstrate that PointMamba achieves superior performance across multiple datasets while significantly reducing GPU memory usage and FLOPs. This work underscores the potential of SSMs in 3D vision-related tasks and presents a simple yet effective Mamba-based baseline for future research. The code will be made available at urlhttps://github.com/LMD0311/PointMamba.

Key facts. Cited by 166 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 72 of its 92 references that are in the map. First posted on arXiv 16 Feb 2024.

Builds on

72 of 92 references.

References · 72

  1. 2017Attention Is All You Needcited by 60,106
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,304
  3. 2020Language Models are Few-Shot Learnerscited by 32,320
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,043
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,111
  6. 2020End-to-End Object Detection with Transformerscited by 7,396
  7. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,364
  8. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,231
  9. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,658
  10. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,389
  11. 2016Gaussian Error Linear Units (GELUs)cited by 3,472
  12. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,889
38 more
  1. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,440
  2. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,326
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,222
  4. 2020GLU Variants Improve Transformercited by 1,759
  5. 2020Point Transformercited by 1,465
  6. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,055
  7. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 976
  8. 2024VMamba: Visual State Space Modelcited by 963
  9. 2022Simplified State Space Layers for Sequence Modelingcited by 781
  10. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  11. 2020PCT: Point cloud transformercited by 731
  12. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 648
  13. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 607
  14. 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 602
  15. 2023Point Transformer V3: Simpler, Faster, Strongercited by 584
  16. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  17. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 457
  18. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  19. 2022On the Parameterization and Initialization of Diagonal State Space Modelscited by 420
  20. 2024U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentationcited by 414
  21. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 385
  22. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  23. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 367
  24. 2022Diagonal State Spaces are as Effective as Structured State Spacescited by 350
  25. 2020Exploring Self-attention for Image Recognitioncited by 313
  26. 2024VM-UNet: Vision Mamba UNet for Medical Image Segmentationcited by 286
  27. 2024SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentationcited by 266
  28. 2022Long Range Language Modeling via Gated State Spacescited by 265
  29. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 263
  30. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  31. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  32. 2024Swin-UMamba: Mamba-based UNet with ImageNet-based pretrainingcited by 179
  33. 2023Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretrainingcited by 162
  34. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  35. 2022Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoderscited by 143
  36. 2020MVTN: Multi-View Transformation Network for 3D Shape Recognitioncited by 140
  37. 2024Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spacescited by 133
  38. 2022How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projectionscited by 121

50 most cited of 72 All 72 (JSON)

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 64; 2025: 69; 2026: 33.

166 papers.

Sort:

By area:

  1. 2024VideoMamba: State Space Model for Efficient Video Understandingcited by 325
  2. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 177
  3. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 109
  4. 2024Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detectioncited by 66
  5. 2024State Space Model for New-Generation Network Alternative to Transformers: A Surveycited by 59
  6. 2024Gamba: Marry Gaussian Splatting with Mamba for single view 3D reconstructioncited by 56
  7. 2024Vision Mamba: A Comprehensive Survey and Taxonomycited by 53
  8. 2025SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretrainingcited by 51
  9. 2024A Survey on Visual Mambacited by 50
  10. 2024Dual-path Mamba: Short and Long-term Bidirectional Selective Structured State Space Models for Speech Separationcited by 45
  11. 2024Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mambacited by 45
  12. 2025MambaHSI: Spatial-Spectral Mamba for Hyperspectral Image Classificationcited by 44
38 more
  1. 2024Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learningcited by 43
  2. 2024LION: Linear Group RNN for 3D Object Detection in Point Cloudscited by 38
  3. 2025The Role of World Models in Shaping Autonomous Driving: A Comprehensive Surveycited by 29
  4. 2024PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysiscited by 26
  5. 2024Matten: Video Generation with Mamba-Attentioncited by 24
  6. 2024NetMamba: Efficient Network Traffic Classification via Pre-training Unidirectional Mambacited by 24
  7. 2025GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generationcited by 23
  8. 2024Mamba-FETrack: Frame-Event Tracking via State Space Modelcited by 22
  9. 2024PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learningcited by 21
  10. 2024Hybrid Mamba for Few-Shot Segmentationcited by 21
  11. 2025UniFuture: A 4D Driving World Model for Future Generation and Perceptioncited by 21
  12. 2024Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and Regression: EventMambacited by 18
  13. 2024Mamba in Vision: A Comprehensive Survey of Techniques and Applicationscited by 18
  14. 2024T-Mamba: A unified framework with Long-Range Dependency in dual-domain for 2D & 3D Tooth Segmentationcited by 17
  15. 2024Text-controlled Motion Mamba: Text-Instructed Temporal Grounding of Human Motioncited by 16
  16. 2024Hi-Mamba: Hierarchical Mamba for Efficient Image Super-Resolutioncited by 16
  17. 2024A Unified Framework for 3D Scene Understandingcited by 15
  18. 2024GroupMamba: Efficient Group-Based Visual State Space Modelcited by 15
  19. 2024MambaTS: Improved Selective State Space Models for Long-term Time Series Forecastingcited by 14
  20. 2024MambaCSR: Dual-Interleaved Scanning for Compressed Image Super-Resolution With SSMscited by 14
  21. 2024ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attentioncited by 13
  22. 2024A Mamba-based Siamese Network for Remote Sensing Change Detectioncited by 13
  23. 2025PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learningcited by 13
  24. 2025FlowRAM: Grounding Flow Matching Policy with Region-Aware Mamba Framework for Robotic Manipulationcited by 13
  25. 2024LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modelingcited by 12
  26. 2024MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretrainingcited by 12
  27. 2024MambaPEFT: Exploring Parameter-Efficient Fine-Tuning for Mambacited by 11
  28. 2024DiMSUM: Diffusion Mamba -- A Scalable and Unified Spatial-Frequency Method for Image Generationcited by 11
  29. 2024A Survey on Multimodal Wearable Sensor-based Human Action Recognitioncited by 10
  30. 2024S2Mamba: A Spatial-spectral State Space Model for Hyperspectral Image Classificationcited by 10
  31. 2024OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene Generationcited by 10
  32. 2025UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detectioncited by 10
  33. 2024QMamba: On First Exploration of Vision Mamba for Image Quality Assessmentcited by 8
  34. 2024PerLA: Perceptive 3D Language Assistantcited by 8
  35. 2025MambaFlow: A Novel and Flow-guided State Space Model for Scene Flow Estimationcited by 8
  36. 2025Revisiting associative recall in modern recurrent modelscited by 7
  37. 2025MoST: Efficient Monarch Sparse Tuning for 3D Representation Learningcited by 6
  38. 2026Mantis: Mamba-native Tuning is Efficient for 3D Point Cloud Foundation Modelscited by 6

50 most cited of 166 All 166 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Point Cloud Mamba: Point Cloud Learning via State Space Model
  2. 2024Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Model
  3. 2024PointABM:Integrating Bidirectional State Space Model with Multi-Head Self-Attention for Point Cloud Analysis
  4. 2025CloudMamba: Grouped Selective State Spaces for Point Cloud Analysis
  5. 2024Pamba: Enhancing Global Interaction in Point Clouds via State Space Model
  6. 2024Point Mamba: A Novel Point Cloud Backbone Based on State Space Model with Octree-Based Ordering Strategy
  7. 20243DMambaIPF: A State Space Model for Iterative Point Cloud Filtering via Differentiable Rendering
  8. 2025Spectral Informed Mamba for Robust Point Cloud Processing