# A-CNN: Annularly Convolutional Neural Networks on Point Clouds

arXiv: https://arxiv.org/abs/1904.08017 · HTML: https://mlsanity.com/paper/1904.08017/

## Key facts

- Cited by 66 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2019.

## Built on by (most cited first, 30 of 66)

- [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)
- [Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline](https://mlsanity.com/paper/2106.05304/) (2021)
- [Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks](https://mlsanity.com/paper/2105.02358/) (2021)
- [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)
- [4D Panoptic LiDAR Segmentation](https://mlsanity.com/paper/2102.12472/) (2021)
- [PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis](https://mlsanity.com/paper/2112.04903/) (2021)
- [Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features](https://mlsanity.com/paper/2311.17024/) (2023)
- [Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling](https://mlsanity.com/paper/2107.02389/) (2021)
- [Neural Points: Point Cloud Representation with Neural Fields for Arbitrary Upsampling](https://mlsanity.com/paper/2112.04148/) (2021)
- [Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models](https://mlsanity.com/paper/2106.04180/) (2021)
- [Deep Learning Based 3D Segmentation: A Survey](https://mlsanity.com/paper/2103.05423/) (2021)
- [Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlook](https://mlsanity.com/paper/2311.02608/) (2023)
- [Clustering based Point Cloud Representation Learning for 3D Analysis](https://mlsanity.com/paper/2307.14605/) (2023)
- [Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective](https://mlsanity.com/paper/2112.12925/) (2021)
- [LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformers](https://mlsanity.com/paper/2210.12755/) (2022)
- [PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning](https://mlsanity.com/paper/2405.15214/) (2024)
- [Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2410.22489/) (2024)
- [Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis](https://mlsanity.com/paper/2212.08892/) (2022)
- [Rethinking Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2403.00592/) (2024)
- [Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition](https://mlsanity.com/paper/2308.09694/) (2023)
- [GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding](https://mlsanity.com/paper/2407.13519/) (2024)
- [Learning without Forgetting for 3D Point Cloud Objects](https://mlsanity.com/paper/2106.14275/) (2021)
- [Language-Level Semantics Conditioned 3D Point Cloud Segmentation](https://mlsanity.com/paper/2107.00430/) (2021)
- [PSNet: Fast Data Structuring for Hierarchical Deep Learning on Point Cloud](https://mlsanity.com/paper/2205.14965/) (2022)
- [Investigate Indistinguishable Points in Semantic Segmentation of 3D Point Cloud](https://mlsanity.com/paper/2103.10339/) (2021)
- [diffConv: Analyzing Irregular Point Clouds with an Irregular View](https://mlsanity.com/paper/2111.14658/) (2021)
- [QuadConv: Quadrature-Based Convolutions with Applications to Non-Uniform PDE Data Compression](https://mlsanity.com/paper/2211.05151/) (2022)
- [Active Self-Training for Weakly Supervised 3D Scene Semantic Segmentation](https://mlsanity.com/paper/2209.07069/) (2022)

## Abstract (arXiv)

Analyzing the geometric and semantic properties of 3D point clouds through the deep networks is still challenging due to the irregularity and sparsity of samplings of their geometric structures. This paper presents a new method to define and compute convolution directly on 3D point clouds by the proposed annular convolution. This new convolution operator can better capture the local neighborhood geometry of each point by specifying the (regular and dilated) ring-shaped structures and directions in the computation. It can adapt to the geometric variability and scalability at the signal processing level. We apply it to the developed hierarchical neural networks for object classification, part segmentation, and semantic segmentation in large-scale scenes. The extensive experiments and comparisons demonstrate that our approach outperforms the state-of-the-art methods on a variety of standard benchmark datasets (e.g., ModelNet10, ModelNet40, ShapeNet-part, S3DIS, and ScanNet).