# ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learning

arXiv: https://arxiv.org/abs/2110.10538 · HTML: https://mlsanity.com/paper/2110.10538/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 48 references that are in the map.
- First posted on arXiv 20 Oct 2021.

## Builds on (most cited first, 30 of 39)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (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)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [DeepGCNs: Can GCNs Go as Deep as CNNs?](https://mlsanity.com/paper/1904.03751/) (2019)
- [Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution](https://mlsanity.com/paper/2007.16100/) (2020)
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://mlsanity.com/paper/1711.09869/) (2017)
- [Relation-Shape Convolutional Neural Network for Point Cloud Analysis](https://mlsanity.com/paper/1904.07601/) (2019)
- [Point-Voxel CNN for Efficient 3D Deep Learning](https://mlsanity.com/paper/1907.03739/) (2019)
- [Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs](https://mlsanity.com/paper/1704.02901/) (2017)
- [SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters](https://mlsanity.com/paper/1803.11527/) (2018)
- [Tangent Convolutions for Dense Prediction in 3D](https://mlsanity.com/paper/1807.02443/) (2018)
- [Deep Parametric Continuous Convolutional Neural Networks](https://mlsanity.com/paper/2101.06742/) (2021)
- [Pointwise Convolutional Neural Networks](https://mlsanity.com/paper/1712.05245/) (2017)

## Built on by (most cited first, 29 of 29)

- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)
- [FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer](https://mlsanity.com/paper/2301.08739/) (2023)
- [PointMixer: MLP-Mixer for Point Cloud Understanding](https://mlsanity.com/paper/2111.11187/) (2021)
- [Point Cloud Mamba: Point Cloud Learning via State Space Model](https://mlsanity.com/paper/2403.00762/) (2024)
- [Meta Architecture for Point Cloud Analysis](https://mlsanity.com/paper/2211.14462/) (2022)
- [PointVector: A Vector Representation In Point Cloud Analysis](https://mlsanity.com/paper/2205.10528/) (2022)
- [Geometric Operator Learning with Optimal Transport](https://mlsanity.com/paper/2507.20065/) (2025)
- [TripNet: Learning Large-scale High-fidelity 3D Car Aerodynamics with Triplane Networks](https://mlsanity.com/paper/2503.17400/) (2025)
- [CP3: Channel Pruning Plug-in for Point-based Networks](https://mlsanity.com/paper/2303.13097/) (2023)
- [S2Contact: Graph-based Network for 3D Hand-Object Contact Estimation with Semi-Supervised Learning](https://mlsanity.com/paper/2208.00874/) (2022)
- [Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud Understanding](https://mlsanity.com/paper/2208.12259/) (2022)
- [Point Deformable Network with Enhanced Normal Embedding for Point Cloud Analysis](https://mlsanity.com/paper/2312.13071/) (2023)
- [GCT: Graph Co-Training for Semi-Supervised Few-Shot Learning](https://mlsanity.com/paper/2203.07738/) (2022)
- [Salient Object Detection for Point Clouds](https://mlsanity.com/paper/2207.11889/) (2022)
- [PointGL: A Simple Global-Local Framework for Efficient Point Cloud Analysis](https://mlsanity.com/paper/2401.11650/) (2024)
- [Collect-and-Distribute Transformer for 3D Point Cloud Analysis](https://mlsanity.com/paper/2306.01257/) (2023)
- [FastPCI: Motion-Structure Guided Fast Point Cloud Frame Interpolation](https://mlsanity.com/paper/2410.19573/) (2024)
- [SAT: Size-Aware Transformer for 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2301.06869/) (2023)
- [PointHR: Exploring High-Resolution Architectures for 3D Point Cloud Segmentation](https://mlsanity.com/paper/2310.07743/) (2023)
- [Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks](https://mlsanity.com/paper/2509.24886/) (2025)
- [Label Name is Mantra: Unifying Point Cloud Segmentation across Heterogeneous Datasets](https://mlsanity.com/paper/2303.10585/) (2023)
- [Rethinking Attention Module Design for Point Cloud Analysis](https://mlsanity.com/paper/2407.19294/) (2024)
- [AVS-Net: Point Sampling with Adaptive Voxel Size for 3D Scene Understanding](https://mlsanity.com/paper/2402.17521/) (2024)
- [Training point-based deep learning networks for forest segmentation with synthetic data](https://mlsanity.com/paper/2403.14115/) (2024)
- [FastPoint: Accelerating 3D Point Cloud Model Inference via Sample Point Distance Prediction](https://mlsanity.com/paper/2507.23480/) (2025)
- [PSFormer: Point Transformer for 3D Salient Object Detection](https://mlsanity.com/paper/2210.15933/) (2022)
- [Efficient Point Cloud Processing with High-Dimensional Positional Encoding and Non-Local MLPs](https://mlsanity.com/paper/2603.04099/) (2026)
- [Beyond Unfolding: 60x Faster One-Stage Unmixing for Closely-Spaced Infrared Small Targets](https://mlsanity.com/paper/2607.16007/) (2026)
- [HGPTrans: Hierarchical Graph-Pooling Transolver for Automotive Aerodynamic Drag Coefficient Prediction](https://mlsanity.com/paper/2609.31765/) (2026)

## Abstract (arXiv)

Access to 3D point cloud representations has been widely facilitated by LiDAR sensors embedded in various mobile devices. This has led to an emerging need for fast and accurate point cloud processing techniques. In this paper, we revisit and dive deeper into PointNet++, one of the most influential yet under-explored networks, and develop faster and more accurate variants of the model. We first present a novel Separable Set Abstraction (SA) module that disentangles the vanilla SA module used in PointNet++ into two separate learning stages: (1) learning channel correlation and (2) learning spatial correlation. The Separable SA module is significantly faster than the vanilla version, yet it achieves comparable performance. We then introduce a new Anisotropic Reduction function into our Separable SA module and propose an Anisotropic Separable SA (ASSA) module that substantially increases the network's accuracy. We later replace the vanilla SA modules in PointNet++ with the proposed ASSA module, and denote the modified network as ASSANet. Extensive experiments on point cloud classification, semantic segmentation, and part segmentation show that ASSANet outperforms PointNet++ and other methods, achieving much higher accuracy and faster speeds. In particular, ASSANet outperforms PointNet++ by 7.4 mIoU on S3DIS Area 5, while maintaining 1.6 ×  faster inference speed on a single NVIDIA 2080Ti GPU. Our scaled ASSANet variant achieves 66.8 mIoU and outperforms KPConv, while being more than 54 × faster.