# A Closer Look at Local Aggregation Operators in Point Cloud Analysis

arXiv: https://arxiv.org/abs/2007.01294 · HTML: https://mlsanity.com/paper/2007.01294/

## Key facts

- Cited by 87 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2020.

## Built on by (most cited first, 30 of 87)

- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)
- [Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework](https://mlsanity.com/paper/2202.07123/) (2022)
- [PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection](https://mlsanity.com/paper/2102.00463/) (2021)
- [Group-Free 3D Object Detection via Transformers](https://mlsanity.com/paper/2104.00678/) (2021)
- [PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds](https://mlsanity.com/paper/2103.14635/) (2021)
- [Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis](https://mlsanity.com/paper/2105.01288/) (2021)
- [Masked Discrimination for Self-Supervised Learning on Point Clouds](https://mlsanity.com/paper/2203.11183/) (2022)
- [Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?](https://mlsanity.com/paper/2212.08320/) (2022)
- [Surface Representation for Point Clouds](https://mlsanity.com/paper/2205.05740/) (2022)
- [PointCutMix: Regularization Strategy for Point Cloud Classification](https://mlsanity.com/paper/2101.01461/) (2021)
- [Deep Learning on Implicit Neural Representations of Shapes](https://mlsanity.com/paper/2302.05438/) (2023)
- [PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis](https://mlsanity.com/paper/2112.04903/) (2021)
- [Contrastive Boundary Learning for Point Cloud Segmentation](https://mlsanity.com/paper/2203.05272/) (2022)
- [PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds](https://mlsanity.com/paper/2305.04925/) (2023)
- [SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation](https://mlsanity.com/paper/2311.17707/) (2023)
- [Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models](https://mlsanity.com/paper/2106.04180/) (2021)
- [Meta Architecture for Point Cloud Analysis](https://mlsanity.com/paper/2211.14462/) (2022)
- [Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis](https://mlsanity.com/paper/2303.08134/) (2023)
- [A Unified Query-based Paradigm for Point Cloud Understanding](https://mlsanity.com/paper/2203.01252/) (2022)
- [Learning Inner-Group Relations on Point Clouds](https://mlsanity.com/paper/2108.12468/) (2021)
- [ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learning](https://mlsanity.com/paper/2110.10538/) (2021)
- [From Multi-View to Hollow-3D: Hallucinated Hollow-3D R-CNN for 3D Object Detection](https://mlsanity.com/paper/2107.14391/) (2021)
- [Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis](https://mlsanity.com/paper/2210.04208/) (2022)
- [SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation](https://mlsanity.com/paper/2105.04447/) (2021)
- [DRINet++: Efficient Voxel-as-point Point Cloud Segmentation](https://mlsanity.com/paper/2111.08318/) (2021)
- [DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentation](https://mlsanity.com/paper/2108.04023/) (2021)
- [PointVector: A Vector Representation In Point Cloud Analysis](https://mlsanity.com/paper/2205.10528/) (2022)
- [Point Cloud Classification Using Content-based Transformer via Clustering in Feature Space](https://mlsanity.com/paper/2303.04599/) (2023)

## Abstract (arXiv)

Recent advances of network architecture for point cloud processing are mainly driven by new designs of local aggregation operators. However, the impact of these operators to network performance is not carefully investigated due to different overall network architecture and implementation details in each solution. Meanwhile, most of operators are only applied in shallow architectures. In this paper, we revisit the representative local aggregation operators and study their performance using the same deep residual architecture. Our investigation reveals that despite the different designs of these operators, all of these operators make surprisingly similar contributions to the network performance under the same network input and feature numbers and result in the state-of-the-art accuracy on standard benchmarks. This finding stimulate us to rethink the necessity of sophisticated design of local aggregation operator for point cloud processing. To this end, we propose a simple local aggregation operator without learnable weights, named Position Pooling (PosPool), which performs similarly or slightly better than existing sophisticated operators. In particular, a simple deep residual network with PosPool layers achieves outstanding performance on all benchmarks, which outperforms the previous state-of-the methods on the challenging PartNet datasets by a large margin (7.4 mIoU). The code is publicly available at https://github.com/zeliu98/CloserLook3D