# PointMixer: MLP-Mixer for Point Cloud Understanding

arXiv: https://arxiv.org/abs/2111.11187 · HTML: https://mlsanity.com/paper/2111.11187/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- Builds on 77 of its 104 references that are in the map.
- First posted on arXiv 22 Nov 2021.

## Builds on (most cited first, 30 of 77)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Efficient Transformers: A Survey](https://mlsanity.com/paper/2009.06732/) (2020)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)

## Built on by (most cited first, 30 of 71)

- [TSMixer: An All-MLP Architecture for Time Series Forecasting](https://mlsanity.com/paper/2303.06053/) (2023)
- [Meta-Transformer: A Unified Framework for Multimodal Learning](https://mlsanity.com/paper/2307.10802/) (2023)
- [Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding](https://mlsanity.com/paper/2304.06906/) (2023)
- [Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2301.10100/) (2023)
- [Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration](https://mlsanity.com/paper/2502.16652/) (2025)
- [Self-positioning Point-based Transformer for Point Cloud Understanding](https://mlsanity.com/paper/2303.16450/) (2023)
- [BALF: Simple and Efficient Blur Aware Local Feature Detector](https://mlsanity.com/paper/2211.14731/) (2022)
- [3D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysis](https://mlsanity.com/paper/2112.04863/) (2021)
- [PointVector: A Vector Representation In Point Cloud Analysis](https://mlsanity.com/paper/2205.10528/) (2022)
- [EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encoder](https://mlsanity.com/paper/2212.04098/) (2022)
- [KPConvX: Modernizing Kernel Point Convolution with Kernel Attention](https://mlsanity.com/paper/2405.13194/) (2024)
- [Deep Point Cloud Reconstruction](https://mlsanity.com/paper/2111.11704/) (2021)
- [Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weather](https://mlsanity.com/paper/2407.02286/) (2024)
- [Accurate and efficient zero-shot 6D pose estimation with frozen foundation models](https://mlsanity.com/paper/2506.09784/) (2025)
- [Decoupled Local Aggregation for Point Cloud Learning](https://mlsanity.com/paper/2308.16532/) (2023)
- [Mixing-Denoising Generalizable Occupancy Networks](https://mlsanity.com/paper/2311.12125/) (2023)
- [Benchmarking tree species classification from proximally-sensed laser scanning data: introducing the FOR-species20K dataset](https://mlsanity.com/paper/2408.06507/) (2024)
- [SummaryMixing: A Linear-Complexity Alternative to Self-Attention for Speech Recognition and Understanding](https://mlsanity.com/paper/2307.07421/) (2023)
- [MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models](https://mlsanity.com/paper/2405.14338/) (2024)
- [PointWavelet: Learning in Spectral Domain for 3D Point Cloud Analysis](https://mlsanity.com/paper/2302.05201/) (2023)
- [You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation](https://mlsanity.com/paper/2304.11762/) (2023)
- [Semantic segmentation of sparse irregular point clouds for leaf/wood discrimination](https://mlsanity.com/paper/2305.16963/) (2023)
- [Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2308.09314/) (2023)
- [FSC: Few-point Shape Completion](https://mlsanity.com/paper/2403.07359/) (2024)
- [Full Point Encoding for Local Feature Aggregation in 3D Point Clouds](https://mlsanity.com/paper/2303.04458/) (2023)
- [Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Models](https://mlsanity.com/paper/2405.14271/) (2024)
- [No Thing, Nothing: Highlighting Safety-Critical Classes for Robust LiDAR Semantic Segmentation in Adverse Weather](https://mlsanity.com/paper/2503.15910/) (2025)
- [Test-Time Augmentation for 3D Point Cloud Classification and Segmentation](https://mlsanity.com/paper/2311.13152/) (2023)
- [Adapt PointFormer: 3D Point Cloud Analysis via Adapting 2D Visual Transformers](https://mlsanity.com/paper/2407.13200/) (2024)
- [Fourier Decomposition for Explicit Representation of 3D Point Cloud Attributes](https://mlsanity.com/paper/2503.10055/) (2025)

## 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.