mlsanityData to 14 Oct 2026

O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis

arXiv 1712.01537 ↗First posted 5 Dec 2017cs.CVcited by 47

Not on the map. Why?

Abstract (arXiv)

We present O-CNN, an Octree-based Convolutional Neural Network (CNN) for 3D shape analysis. Built upon the octree representation of 3D shapes, our method takes the average normal vectors of a 3D model sampled in the finest leaf octants as input and performs 3D CNN operations on the octants occupied by the 3D shape surface. We design a novel octree data structure to efficiently store the octant information and CNN features into the graphics memory and execute the entire O-CNN training and evaluation on the GPU. O-CNN supports various CNN structures and works for 3D shapes in different representations. By restraining the computations on the octants occupied by 3D surfaces, the memory and computational costs of the O-CNN grow quadratically as the depth of the octree increases, which makes the 3D CNN feasible for high-resolution 3D models. We compare the performance of the O-CNN with other existing 3D CNN solutions and demonstrate the efficiency and efficacy of O-CNN in three shape analysis tasks, including object classification, shape retrieval, and shape segmentation.

Key facts. Cited by 47 papers in the map (data through 14 Oct 2026). First posted on arXiv 5 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 21; 2022: 19; 2023: 7.

47 papers.

Sort:

  1. 2022Mask3D: Mask Transformer for 3D Semantic Instance Segmentationcited by 303
  2. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 286
  3. 2023Locally Attentional SDF Diffusion for Controllable 3D Shape Generationcited by 130
  4. 2021HDR-NeRF: High Dynamic Range Neural Radiance Fieldscited by 114
  5. 2022Surface Representation for Point Cloudscited by 84
  6. 2021Subdivision-Based Mesh Convolution Networkscited by 60
  7. 2022Contrastive Boundary Learning for Point Cloud Segmentationcited by 56
  8. 2021Multiresolution Deep Implicit Functions for 3D Shape Representationcited by 35
  9. 2022Enable Deep Learning on Mobile Devices: Methods, Systems, and Applicationscited by 32
  10. 2022CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representationscited by 31
  11. 2021Learning Inner-Group Relations on Point Cloudscited by 29
  12. 2022RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learningcited by 29
35 more
  1. 2021Spatial-Temporal Transformer for 3D Point Cloud Sequencescited by 22
  2. 2022Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Imagescited by 21
  3. 2022Point Scene Understanding via Disentangled Instance Mesh Reconstructioncited by 20
  4. 2022Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysiscited by 19
  5. 2022DArch: Dental Arch Prior-assisted 3D Tooth Instance Segmentationcited by 18
  6. 2022PVNAS: 3D Neural Architecture Search with Point-Voxel Convolutioncited by 16
  7. 2022AGConv: Adaptive Graph Convolution on 3D Point Cloudscited by 13
  8. 2021Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networkscited by 12
  9. 20213D Instance Segmentation of MVS Buildingscited by 12
  10. 2021PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representationcited by 9
  11. 2022Semi-supervised 3D shape segmentation with multilevel consistency and part substitutioncited by 8
  12. 2022LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modelingcited by 8
  13. 2021Learning without Forgetting for 3D Point Cloud Objectscited by 7
  14. 2022PSNet: Fast Data Structuring for Hierarchical Deep Learning on Point Cloudcited by 7
  15. 2022Keypoint Cascade Voting for Point Cloud Based 6DoF Pose Estimationcited by 7
  16. 2021Learning Mesh Representations via Binary Space Partitioning Tree Networkscited by 5
  17. 2023Transient Hemodynamics Prediction Using an Efficient Octree-Based Deep Learning Modelcited by 5
  18. 2021Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data via Differentiable Cross-Approximationcited by 4
  19. 2022PointSCNet: Point Cloud Structure and Correlation Learning Based on Space Filling Curve-Guided Samplingcited by 4
  20. 2021Black-Box Test-Time Shape REFINEment for Single View 3D Reconstructioncited by 3
  21. 2022High-fidelity 3D Model Compression based on Key Spherescited by 3
  22. 2023A Review of Deep Learning-Powered Mesh Reconstruction Methodscited by 3
  23. 2023Learning Versatile 3D Shape Generation with Improved AR Modelscited by 3
  24. 2023PatchMixer: Rethinking network design to boost generalization for 3D point cloud understandingcited by 3
  25. 20213D Meta-Segmentation Neural Networkcited by 2
  26. 2023DANet: Density Adaptive Convolutional Network with Interactive Attention for 3D Point Cloudscited by 2
  27. 2021EllipsoidNet: Ellipsoid Representation for Point Cloud Classification and Segmentationcited by 1
  28. 2021S-AT GCN: Spatial-Attention Graph Convolution Network based Feature Enhancement for 3D Object Detectioncited by 1
  29. 2021ActivationNet: Representation learning to predict contact quality of interacting 3-D surfaces in engineering designscited by 1
  30. 2021Robust Pooling through the Data Modecited by 1
  31. 2021Interpolation-Aware Padding for 3D Sparse Convolutional Neural Networkscited by 1
  32. 2021Two Heads are Better than One: Geometric-Latent Attention for Point Cloud Classification and Segmentationcited by 1
  33. 2021Robust 3D Scene Segmentation through Hierarchical and Learnable Part-Fusioncited by 1
  34. 2022Multi-view Attention for gestational age at birth predictioncited by 0
  35. 2023Semantic Segmentation of Urban Textured Meshes Through Point Samplingcited by 0