mlsanityData to 7 Oct 2026

Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework

arXiv 2202.07123 ↗First posted 15 Feb 2022cs.CV cs.AIcited by 376

Not on the map. Why?

Abstract (arXiv)

Point cloud analysis is challenging due to irregularity and unordered data structure. To capture the 3D geometries, prior works mainly rely on exploring sophisticated local geometric extractors using convolution, graph, or attention mechanisms. These methods, however, incur unfavorable latency during inference, and the performance saturates over the past few years. In this paper, we present a novel perspective on this task. We notice that detailed local geometrical information probably is not the key to point cloud analysis -- we introduce a pure residual MLP network, called PointMLP, which integrates no sophisticated local geometrical extractors but still performs very competitively. Equipped with a proposed lightweight geometric affine module, PointMLP delivers the new state-of-the-art on multiple datasets. On the real-world ScanObjectNN dataset, our method even surpasses the prior best method by 3.3% accuracy. We emphasize that PointMLP achieves this strong performance without any sophisticated operations, hence leading to a superior inference speed. Compared to most recent CurveNet, PointMLP trains 2x faster, tests 7x faster, and is more accurate on ModelNet40 benchmark. We hope our PointMLP may help the community towards a better understanding of point cloud analysis. The code is available at https://github.com/ma-xu/pointMLP-pytorch.

Key facts. Cited by 376 papers in the map (data through 7 Oct 2026). Builds on 53 of its 65 references that are in the map. First posted on arXiv 15 Feb 2022.

Builds on

53 of 65 references.

References · 53

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  7. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  8. 2017Squeeze-and-Excitation Networkscited by 4,763
  9. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  10. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  11. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  12. 2017Non-local Neural Networkscited by 2,290
38 more
  1. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  2. 2018Group Normalizationcited by 1,514
  3. 2020Point Transformercited by 1,462
  4. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  5. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  6. 2017Visualizing the Loss Landscape of Neural Netscited by 1,126
  7. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  8. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  9. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  10. 2020PCT: Point cloud transformercited by 730
  11. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  12. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  13. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  14. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  15. 2020ResNeSt: Split-Attention Networkscited by 445
  16. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  17. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 338
  18. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  19. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  20. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  21. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  22. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  23. 2021Group-Free 3D Object Detection via Transformerscited by 215
  24. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  25. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  26. 2020SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentationcited by 170
  27. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  28. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  29. 2020MVTN: Multi-View Transformation Network for 3D Shape Recognitioncited by 140
  30. 2021LiDAR R-CNN: An Efficient and Universal 3D Object Detectorcited by 129
  31. 2019DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processingcited by 104
  32. 2020A Closer Look at Local Aggregation Operators in Point Cloud Analysiscited by 87
  33. 2019DeepGCNs: Making GCNs Go as Deep as CNNscited by 72
  34. 2020Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloudcited by 71
  35. 2016SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentationcited by 70
  36. 2021PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysiscited by 58
  37. 2020End-to-End Learning Local Multi-view Descriptors for 3D Point Cloudscited by 47
  38. 2020Dense-Resolution Network for Point Cloud Classification and Segmentationcited by 45

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 46; 2023: 107; 2024: 106; 2025: 67; 2026: 50.

376 papers.

Sort:

By area:

  1. 2023Point Transformer V3: Simpler, Faster, Strongercited by 579
  2. 2023Ferret: Refer and Ground Anything Anywhere at Any Granularitycited by 498
  3. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  4. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 262
  5. 2023Uni3D: Exploring Unified 3D Representation at Scalecited by 231
  6. 2023MVImgNet: A Large-scale Dataset of Multi-view Imagescited by 219
  7. 2023ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understandingcited by 199
  8. 2022PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learningcited by 186
  9. 2023OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understandingcited by 183
  10. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 175
  11. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 166
  12. 2023Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretrainingcited by 162
38 more
  1. 2022Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoderscited by 143
  2. 2023Meta-Transformer: A Unified Framework for Multimodal Learningcited by 136
  3. 2024ShapeLLM: Universal 3D Object Understanding for Embodied Interactioncited by 133
  4. 2022Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?cited by 121
  5. 2023PointGPT: Auto-regressively Generative Pre-training from Point Cloudscited by 115
  6. 2025Sonata: Self-Supervised Learning of Reliable Point Representationscited by 108
  7. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 105
  8. 2023CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognitioncited by 77
  9. 2022P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Promptingcited by 74
  10. 2023Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Modelscited by 67
  11. 2024Point Cloud Mamba: Point Cloud Learning via State Space Modelcited by 66
  12. 2023Grounding 3D Object Affordance from 2D Interactions in Imagescited by 62
  13. 2023Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Reviewcited by 57
  14. 2024Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Modelcited by 57
  15. 2023Using a Waffle Iron for Automotive Point Cloud Semantic Segmentationcited by 53
  16. 2024Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysiscited by 52
  17. 2022A Comprehensive Survey on Deep Gait Recognition: Algorithms, Datasets and Challengescited by 45
  18. 2023SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentationcited by 44
  19. 2023Image as Set of Pointscited by 43
  20. 2024Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learningcited by 43
  21. 2023Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoderscited by 42
  22. 2023Self-positioning Point-based Transformer for Point Cloud Understandingcited by 40
  23. 2023Explore In-Context Learning for 3D Point Cloud Understandingcited by 40
  24. 2022Meta Architecture for Point Cloud Analysiscited by 39
  25. 2023Smooth, exact rotational symmetrization for deep learning on point cloudscited by 39
  26. 2023Frozen Transformers in Language Models Are Effective Visual Encoder Layerscited by 39
  27. 2023Sketch and Text Guided Diffusion Model for Colored Point Cloud Generationcited by 36
  28. 2023Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysiscited by 34
  29. 2023WaterScenes: A Multi-Task 4D Radar-Camera Fusion Dataset and Benchmarks for Autonomous Driving on Water Surfacescited by 34
  30. 2023Spiking PointNet: Spiking Neural Networks for Point Cloudscited by 34
  31. 2022PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detectioncited by 33
  32. 2022Transformers in 3D Point Clouds: A Surveycited by 31
  33. 2023SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognitioncited by 30
  34. 2024Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detectioncited by 30
  35. 2023ViT-Lens: Towards Omni-modal Representationscited by 29
  36. 2023Point2Vec for Self-Supervised Representation Learning on Point Cloudscited by 28
  37. 2024TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understandingcited by 26
  38. 2024PoinTramba: A Hybrid Transformer-Mamba Framework for Point Cloud Analysiscited by 26

50 most cited of 376 All 376 (JSON)