# Octree guided CNN with Spherical Kernels for 3D Point Clouds

arXiv: https://arxiv.org/abs/1903.00343 · HTML: https://mlsanity.com/paper/1903.00343/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2019.

## Built on by (most cited first, 30 of 50)

- [Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis](https://mlsanity.com/paper/2105.01288/) (2021)
- [OctFormer: Octree-based Transformers for 3D Point Clouds](https://mlsanity.com/paper/2305.03045/) (2023)
- [Understanding Pooling in Graph Neural Networks](https://mlsanity.com/paper/2110.05292/) (2021)
- [Regularization Strategy for Point Cloud via Rigidly Mixed Sample](https://mlsanity.com/paper/2102.01929/) (2021)
- [PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis](https://mlsanity.com/paper/2112.04903/) (2021)
- [OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression](https://mlsanity.com/paper/2202.06028/) (2022)
- [Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling](https://mlsanity.com/paper/2107.02389/) (2021)
- [OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries](https://mlsanity.com/paper/2312.03774/) (2023)
- [GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2305.16404/) (2023)
- [Deep Learning Based 3D Segmentation: A Survey](https://mlsanity.com/paper/2103.05423/) (2021)
- [Dual Transformer for Point Cloud Analysis](https://mlsanity.com/paper/2104.13044/) (2021)
- [Clustering based Point Cloud Representation Learning for 3D Analysis](https://mlsanity.com/paper/2307.14605/) (2023)
- [Efficient and Robust LiDAR-Based End-to-End Navigation](https://mlsanity.com/paper/2105.09932/) (2021)
- [PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution](https://mlsanity.com/paper/2204.11797/) (2022)
- [ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding](https://mlsanity.com/paper/2312.11112/) (2023)
- [Point Cloud Learning with Transformer](https://mlsanity.com/paper/2104.13636/) (2021)
- [HyperPocket: Generative Point Cloud Completion](https://mlsanity.com/paper/2102.05973/) (2021)
- [SageMix: Saliency-Guided Mixup for Point Clouds](https://mlsanity.com/paper/2210.06944/) (2022)
- [DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds](https://mlsanity.com/paper/2111.08799/) (2021)
- [RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut 2D-Tree Representation](https://mlsanity.com/paper/2104.05328/) (2021)
- [LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2506.07857/) (2025)
- [Language-Level Semantics Conditioned 3D Point Cloud Segmentation](https://mlsanity.com/paper/2107.00430/) (2021)
- [LinK3D: Linear Keypoints Representation for 3D LiDAR Point Cloud](https://mlsanity.com/paper/2206.05927/) (2022)
- [Salient Object Detection for Point Clouds](https://mlsanity.com/paper/2207.11889/) (2022)
- [CurveCloudNet: Processing Point Clouds with 1D Structure](https://mlsanity.com/paper/2303.12050/) (2023)
- [Picasso: A CUDA-based Library for Deep Learning over 3D Meshes](https://mlsanity.com/paper/2103.15076/) (2021)
- [CloudWalker: Random walks for 3D point cloud shape analysis](https://mlsanity.com/paper/2112.01050/) (2021)
- [Mesh Convolution with Continuous Filters for 3D Surface Parsing](https://mlsanity.com/paper/2112.01801/) (2021)
- [COLA: COarse LAbel pre-training for 3D semantic segmentation of sparse LiDAR datasets](https://mlsanity.com/paper/2202.06884/) (2022)
- [PDF: A Probability-Driven Framework for Open World 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2404.00979/) (2024)

## Abstract (arXiv)

We propose an octree guided neural network architecture and spherical convolutional kernel for machine learning from arbitrary 3D point clouds. The network architecture capitalizes on the sparse nature of irregular point clouds, and hierarchically coarsens the data representation with space partitioning. At the same time, the proposed spherical kernels systematically quantize point neighborhoods to identify local geometric structures in the data, while maintaining the properties of translation-invariance and asymmetry. We specify spherical kernels with the help of network neurons that in turn are associated with spatial locations. We exploit this association to avert dynamic kernel generation during network training that enables efficient learning with high resolution point clouds. The effectiveness of the proposed technique is established on the benchmark tasks of 3D object classification and segmentation, achieving new state-of-the-art on ShapeNet and RueMonge2014 datasets.