mlsanityData to 7 Oct 2026

PointMixer: MLP-Mixer for Point Cloud Understanding

arXiv 2111.11187 ↗First posted 22 Nov 2021cs.CVcited by 71

Not on the map. Why?

Abstract (arXiv)

MLP-Mixer has newly appeared as a new challenger against the realm of CNNs and transformer. Despite its simplicity compared to transformer, the concept of channel-mixing MLPs and token-mixing MLPs achieves noticeable performance in visual recognition tasks. Unlike images, point clouds are inherently sparse, unordered and irregular, which limits the direct use of MLP-Mixer for point cloud understanding. In this paper, we propose PointMixer, a universal point set operator that facilitates information sharing among unstructured 3D points. By simply replacing token-mixing MLPs with a softmax function, PointMixer can "mix" features within/between point sets. By doing so, PointMixer can be broadly used in the network as inter-set mixing, intra-set mixing, and pyramid mixing. Extensive experiments show the competitive or superior performance of PointMixer in semantic segmentation, classification, and point reconstruction against transformer-based methods.

Key facts. Cited by 71 papers in the map (data through 7 Oct 2026). Builds on 77 of its 104 references that are in the map. First posted on arXiv 22 Nov 2021.

Builds on

77 of 104 references.

References · 77

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  8. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  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. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  12. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
38 more
  1. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  2. 2017Billion-scale similarity search with GPUscited by 2,477
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  4. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  5. 2020Point Transformercited by 1,462
  6. 2021MLP-Mixer: An all-MLP Architecture for Visioncited by 1,441
  7. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  8. 2018On the Spectral Bias of Neural Networkscited by 1,321
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  10. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  11. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  12. 2021Transformers in Vision: A Surveycited by 1,009
  13. 2021CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classificationcited by 806
  14. 2020Efficient Transformers: A Surveycited by 784
  15. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  16. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  17. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  18. 2020PCT: Point cloud transformercited by 730
  19. 2018Open3D: A Modern Library for 3D Data Processingcited by 717
  20. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  21. 2021Transformer in Transformercited by 632
  22. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  23. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  24. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  25. 2021ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biasescited by 484
  26. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  27. 2021Pay Attention to MLPscited by 367
  28. 2015Learning Deconvolution Network for Semantic Segmentationcited by 365
  29. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  30. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  31. 2021ResMLP: Feedforward networks for image classification with data-efficient trainingcited by 338
  32. 2020Exploring Self-attention for Image Recognitioncited by 313
  33. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  34. 2021Voxel Transformer for 3D Object Detectioncited by 247
  35. 2017Submanifold Sparse Convolutional Networkscited by 223
  36. 2021Scaling Local Self-Attention for Parameter Efficient Visual Backbonescited by 220
  37. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  38. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210

50 most cited of 77 All 77 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 4; 2023: 24; 2024: 18; 2025: 11; 2026: 11.

71 papers.

Sort:

By area:

  1. 2023TSMixer: An All-MLP Architecture for Time Series Forecastingcited by 232
  2. 2023Meta-Transformer: A Unified Framework for Multimodal Learningcited by 136
  3. 2023Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understandingcited by 111
  4. 2023Using a Waffle Iron for Automotive Point Cloud Semantic Segmentationcited by 53
  5. 2025Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registrationcited by 50
  6. 2023Self-positioning Point-based Transformer for Point Cloud Understandingcited by 40
  7. 2022BALF: Simple and Efficient Blur Aware Local Feature Detectorcited by 34
  8. 20213D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysiscited by 23
  9. 2022PointVector: A Vector Representation In Point Cloud Analysiscited by 21
  10. 2022EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encodercited by 18
  11. 2024KPConvX: Modernizing Kernel Point Convolution with Kernel Attentioncited by 16
  12. 2021Deep Point Cloud Reconstructioncited by 15
38 more
  1. 2024Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weathercited by 14
  2. 2025Accurate and efficient zero-shot 6D pose estimation with frozen foundation modelscited by 13
  3. 2023Decoupled Local Aggregation for Point Cloud Learningcited by 12
  4. 2023Mixing-Denoising Generalizable Occupancy Networkscited by 12
  5. 2024Benchmarking tree species classification from proximally-sensed laser scanning data: introducing the FOR-species20K datasetcited by 12
  6. 2023SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understandingcited by 11
  7. 2024MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Modelscited by 11
  8. 2023PointWavelet: Learning in Spectral Domain for 3D Point Cloud Analysiscited by 7
  9. 2023You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentationcited by 6
  10. 2023Semantic segmentation of sparse irregular point clouds for leaf/wood discriminationcited by 6
  11. 2023Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentationcited by 6
  12. 2024FSC: Few-point Shape Completioncited by 6
  13. 2023Full Point Encoding for Local Feature Aggregation in 3D Point Cloudscited by 5
  14. 2024Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Modelscited by 5
  15. 2025No Thing, Nothing: Highlighting Safety-Critical Classes for Robust LiDAR Semantic Segmentation in Adverse Weathercited by 5
  16. 2023Test-Time Augmentation for 3D Point Cloud Classification and Segmentationcited by 4
  17. 2024Adapt PointFormer: 3D Point Cloud Analysis via Adapting 2D Visual Transformerscited by 4
  18. 2025Fourier Decomposition for Explicit Representation of 3D Point Cloud Attributescited by 4
  19. 2023Asynchronous Events-based Panoptic Segmentation using Graph Mixer Neural Networkcited by 3
  20. 2023Object Re-Identification from Point Cloudscited by 3
  21. 2023Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learningcited by 3
  22. 2023PatchMixer: Rethinking network design to boost generalization for 3D point cloud understandingcited by 3
  23. 2023PointHR: Exploring High-Resolution Architectures for 3D Point Cloud Segmentationcited by 3
  24. 2024Advancements in Point Cloud-Based 3D Defect Detection and Classification for Industrial Systems: A Comprehensive Surveycited by 3
  25. 2024GeoAuxNet: Towards Universal 3D Representation Learning for Multi-sensor Point Cloudscited by 3
  26. 2024Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transformcited by 3
  27. 2024Is Contrastive Distillation Enough for Learning Comprehensive 3D Representations?cited by 3
  28. 2021Putting 3D Spatially Sparse Networks on a Dietcited by 2
  29. 2023SelFLoc: Selective Feature Fusion for Large-scale Point Cloud-based Place Recognitioncited by 2
  30. 2024APC2Mesh: Bridging the gap from occluded building faccades to full 3D modelscited by 2
  31. 2024PointViG: A Lightweight GNN-based Model for Efficient Point Cloud Analysiscited by 2
  32. 2025Mesh Mamba: A Unified State Space Model for Saliency Prediction in Non-Textured and Textured Meshescited by 2
  33. 2023Cloud-RAIN: Point Cloud Analysis with Reflectional Invariancecited by 1
  34. 2025Is clustering enough for LiDAR instance segmentation? A state-of-the-art training-free baselinecited by 1
  35. 2025Ambiguity-aware Point Cloud Segmentation by Adaptive Margin Contrastive Learningcited by 1
  36. 2026STS-Mixer: Spatio-Temporal-Spectral Mixer for 4D Point Cloud Video Understandingcited by 1
  37. 2022Diffusion Unit: Interpretable Edge Enhancement and Suppression Learning for 3D Point Cloud Segmentationcited by 0
  38. 2023APPT : Asymmetric Parallel Point Transformer for 3D Point Cloud Understandingcited by 0

50 most cited of 71 All 71 (JSON)