# Learning Inner-Group Relations on Point Clouds

arXiv: https://arxiv.org/abs/2108.12468 · HTML: https://mlsanity.com/paper/2108.12468/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- Builds on 52 of its 65 references that are in the map.
- First posted on arXiv 27 Aug 2021.

## Builds on (most cited first, 30 of 52)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (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)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (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)
- [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)
- [Stand-Alone Self-Attention in Vision Models](https://mlsanity.com/paper/1906.05909/) (2019)
- [Residual Attention Network for Image Classification](https://mlsanity.com/paper/1704.06904/) (2017)
- [Attention Augmented Convolutional Networks](https://mlsanity.com/paper/1904.09925/) (2019)
- [Relation-Shape Convolutional Neural Network for Point Cloud Analysis](https://mlsanity.com/paper/1904.07601/) (2019)
- [OctNet: Learning Deep 3D Representations at High Resolutions](https://mlsanity.com/paper/1611.05009/) (2016)
- [Exploring Self-attention for Image Recognition](https://mlsanity.com/paper/2004.13621/) (2020)
- [Relation Networks for Object Detection](https://mlsanity.com/paper/1711.11575/) (2017)
- [SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters](https://mlsanity.com/paper/1803.11527/) (2018)
- [Volumetric and Multi-View CNNs for Object Classification on 3D Data](https://mlsanity.com/paper/1604.03265/) (2016)
- [PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling](https://mlsanity.com/paper/2003.00492/) (2020)

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

- [Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework](https://mlsanity.com/paper/2202.07123/) (2022)
- [ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding](https://mlsanity.com/paper/2212.05171/) (2022)
- [Surface Representation for Point Clouds](https://mlsanity.com/paper/2205.05740/) (2022)
- [Self-positioning Point-based Transformer for Point Cloud Understanding](https://mlsanity.com/paper/2303.16450/) (2023)
- [Transformers in 3D Point Clouds: A Survey](https://mlsanity.com/paper/2205.07417/) (2022)
- [Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlook](https://mlsanity.com/paper/2311.02608/) (2023)
- [FBNet: Feedback Network for Point Cloud Completion](https://mlsanity.com/paper/2210.03974/) (2022)
- [Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2410.22489/) (2024)
- [Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space](https://mlsanity.com/paper/2303.04599/) (2023)
- [SE-ORNet: Self-Ensembling Orientation-aware Network for Unsupervised Point Cloud Shape Correspondence](https://mlsanity.com/paper/2304.05395/) (2023)
- [Rethinking Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2403.00592/) (2024)
- [LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels](https://mlsanity.com/paper/2403.15173/) (2024)
- [Instant4D: 4D Gaussian Splatting in Minutes](https://mlsanity.com/paper/2510.01119/) (2025)
- [PointGL: A Simple Global-Local Framework for Efficient Point Cloud Analysis](https://mlsanity.com/paper/2401.11650/) (2024)
- [CloudWalker: Random walks for 3D point cloud shape analysis](https://mlsanity.com/paper/2112.01050/) (2021)
- [PointSCNet: Point Cloud Structure and Correlation Learning Based on Space Filling Curve-Guided Sampling](https://mlsanity.com/paper/2202.10251/) (2022)
- [APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud Classification](https://mlsanity.com/paper/2205.00847/) (2022)
- [Composite Convolution: a Flexible Operator for Deep Learning on 3D Point Clouds](https://mlsanity.com/paper/2209.11796/) (2022)
- [PointNorm: Dual Normalization is All You Need for Point Cloud Analysis](https://mlsanity.com/paper/2207.06324/) (2022)
- [PIDS: Joint Point Interaction-Dimension Search for 3D Point Cloud](https://mlsanity.com/paper/2211.15759/) (2022)
- [SAT: Size-Aware Transformer for 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2301.06869/) (2023)
- [3D Object Detection from Point Cloud via Voting Step Diffusion](https://mlsanity.com/paper/2403.14133/) (2024)
- [PointCAT: Cross-Attention Transformer for point cloud](https://mlsanity.com/paper/2304.03012/) (2023)
- [Point Cloud Recognition with Position-to-Structure Attention Transformers](https://mlsanity.com/paper/2210.02030/) (2022)
- [PointeNet: A Lightweight Framework for Effective and Efficient Point Cloud Analysis](https://mlsanity.com/paper/2312.12743/) (2023)
- [3D Test-time Adaptation via Graph Spectral Driven Point Shift](https://mlsanity.com/paper/2507.18225/) (2025)
- [Adaptive Edge-to-Edge Interaction Learning for Point Cloud Analysis](https://mlsanity.com/paper/2211.10888/) (2022)
- [Feature Adversarial Distillation for Point Cloud Classification](https://mlsanity.com/paper/2306.14221/) (2023)
- [BAGNet: A Boundary-Aware Graph Attention Network for 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2506.00475/) (2025)

## Abstract (arXiv)

The prevalence of relation networks in computer vision is in stark contrast to underexplored point-based methods. In this paper, we explore the possibilities of local relation operators and survey their feasibility. We propose a scalable and efficient module, called group relation aggregator. The module computes a feature of a group based on the aggregation of the features of the inner-group points weighted by geometric relations and semantic relations. We adopt this module to design our RPNet. We further verify the expandability of RPNet, in terms of both depth and width, on the tasks of classification and segmentation. Surprisingly, empirical results show that wider RPNet fits for classification, while deeper RPNet works better on segmentation. RPNet achieves state-of-the-art for classification and segmentation on challenging benchmarks. We also compare our local aggregator with PointNet++, with around 30% parameters and 50% computation saving. Finally, we conduct experiments to reveal the robustness of RPNet with regard to rigid transformation and noises.