mlsanityData to 14 Oct 2026

Octree guided CNN with Spherical Kernels for 3D Point Clouds

arXiv 1903.00343 ↗First posted 28 Feb 2019cs.CVcited by 50

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 24; 2022: 8; 2023: 10; 2024: 2; 2025: 4; 2026: 2.

50 papers.

Sort:

By area:

  1. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  2. 2023OctFormer: Octree-based Transformers for 3D Point Cloudscited by 109
  3. 2021Understanding Pooling in Graph Neural Networkscited by 69
  4. 2021Regularization Strategy for Point Cloud via Rigidly Mixed Samplecited by 59
  5. 2021PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysiscited by 58
  6. 2022OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compressioncited by 58
  7. 2021Learning Semantic Segmentation of Large-Scale Point Clouds with Random Samplingcited by 51
  8. 2023OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queriescited by 48
  9. 2023GrowSP: Unsupervised Semantic Segmentation of 3D Point Cloudscited by 34
  10. 2021Deep Learning Based 3D Segmentation: A Surveycited by 30
  11. 2021Dual Transformer for Point Cloud Analysiscited by 26
  12. 2023Clustering based Point Cloud Representation Learning for 3D Analysiscited by 23
38 more
  1. 2021Efficient and Robust LiDAR-Based End-to-End Navigationcited by 22
  2. 2022PVNAS: 3D Neural Architecture Search with Point-Voxel Convolutioncited by 16
  3. 2023ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understandingcited by 16
  4. 2021Point Cloud Learning with Transformercited by 15
  5. 2021HyperPocket: Generative Point Cloud Completioncited by 12
  6. 2022SageMix: Saliency-Guided Mixup for Point Cloudscited by 12
  7. 2021DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Cloudscited by 10
  8. 2021RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut 2D-Tree Representationcited by 8
  9. 2025LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Cloudscited by 8
  10. 2021Language-Level Semantics Conditioned 3D Point Cloud Segmentationcited by 7
  11. 2022LinK3D: Linear Keypoints Representation for 3D LiDAR Point Cloudcited by 5
  12. 2022Salient Object Detection for Point Cloudscited by 5
  13. 2023CurveCloudNet: Processing Point Clouds with 1D Structurecited by 5
  14. 2021Picasso: A CUDA-based Library for Deep Learning over 3D Meshescited by 4
  15. 2021CloudWalker: Random walks for 3D point cloud shape analysiscited by 4
  16. 2021Mesh Convolution with Continuous Filters for 3D Surface Parsingcited by 4
  17. 2022COLA: COarse LAbel pre-training for 3D semantic segmentation of sparse LiDAR datasetscited by 4
  18. 2024PDF: A Probability-Driven Framework for Open World 3D Point Cloud Semantic Segmentationcited by 4
  19. 2025Mitigating Ambiguities in 3D Classification with Gaussian Splattingcited by 4
  20. 2021Dynamic Convolution for 3D Point Cloud Instance Segmentationcited by 3
  21. 2021Differentiable Convolution Search for Point Cloud Processingcited by 3
  22. 2021Multi Point-Voxel Convolution (MPVConv) for Deep Learning on Point Cloudscited by 2
  23. 2021VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentationcited by 2
  24. 2022DOTIN: Dropping Task-Irrelevant Nodes for GNNscited by 2
  25. 2023SphereNet: Learning a Noise-Robust and General Descriptor for Point Cloud Registrationcited by 2
  26. 2025Occlusion-aware Text-Image-Point Cloud Pretraining for Open-World 3D Object Recognitioncited by 2
  27. 2021EllipsoidNet: Ellipsoid Representation for Point Cloud Classification and Segmentationcited by 1
  28. 2021Revisiting 2D Convolutional Neural Networks for Graph-based Applicationscited by 1
  29. 2022PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Treescited by 1
  30. 2023Semantic Segmentation on 3D Point Clouds with High Density Variationscited by 1
  31. 2023Find the Lady: Permutation and Re-Synchronization of Deep Neural Networkscited by 1
  32. 2021Probability-Generating Function Kernels for Spherical Datacited by 0
  33. 2021Variance-Aware Weight Initialization for Point Convolutional Neural Networkscited by 0
  34. 2023Point Neighborhood Embeddingscited by 0
  35. 2024Soft Masked Transformer for Point Cloud Processing with Skip Attention-Based Upsamplingcited by 0
  36. 2025SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Cloudscited by 0
  37. 2026Efficient Point Cloud Processing with High-Dimensional Positional Encoding and Non-Local MLPscited by 0
  38. 2026GIBLy: Improving 3D Semantic Segmentation through an Architecture-Agnostic Lightweight Geometric Inductive Bias Layercited by 0