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

arXiv: https://arxiv.org/abs/1712.01537 · HTML: https://mlsanity.com/paper/1712.01537/

## Key facts

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

## Built on by (most cited first, 30 of 47)

- [Mask3D: Mask Transformer for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2210.03105/) (2022)
- [PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers](https://mlsanity.com/paper/2108.08839/) (2021)
- [Locally Attentional SDF Diffusion for Controllable 3D Shape Generation](https://mlsanity.com/paper/2305.04461/) (2023)
- [HDR-NeRF: High Dynamic Range Neural Radiance Fields](https://mlsanity.com/paper/2111.14451/) (2021)
- [Surface Representation for Point Clouds](https://mlsanity.com/paper/2205.05740/) (2022)
- [Subdivision-Based Mesh Convolution Networks](https://mlsanity.com/paper/2106.02285/) (2021)
- [Contrastive Boundary Learning for Point Cloud Segmentation](https://mlsanity.com/paper/2203.05272/) (2022)
- [Multiresolution Deep Implicit Functions for 3D Shape Representation](https://mlsanity.com/paper/2109.05591/) (2021)
- [Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications](https://mlsanity.com/paper/2204.11786/) (2022)
- [CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representations](https://mlsanity.com/paper/2208.10555/) (2022)
- [Learning Inner-Group Relations on Point Clouds](https://mlsanity.com/paper/2108.12468/) (2021)
- [RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning](https://mlsanity.com/paper/2202.13094/) (2022)
- [Spatial-Temporal Transformer for 3D Point Cloud Sequences](https://mlsanity.com/paper/2110.09783/) (2021)
- [Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Images](https://mlsanity.com/paper/2204.09866/) (2022)
- [Point Scene Understanding via Disentangled Instance Mesh Reconstruction](https://mlsanity.com/paper/2203.16832/) (2022)
- [Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis](https://mlsanity.com/paper/2212.08892/) (2022)
- [DArch: Dental Arch Prior-assisted 3D Tooth Instance Segmentation](https://mlsanity.com/paper/2204.11911/) (2022)
- [PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution](https://mlsanity.com/paper/2204.11797/) (2022)
- [AGConv: Adaptive Graph Convolution on 3D Point Clouds](https://mlsanity.com/paper/2206.04665/) (2022)
- [Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks](https://mlsanity.com/paper/2101.00483/) (2021)
- [3D Instance Segmentation of MVS Buildings](https://mlsanity.com/paper/2112.09902/) (2021)
- [PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation](https://mlsanity.com/paper/2110.07882/) (2021)
- [Semi-supervised 3D shape segmentation with multilevel consistency and part substitution](https://mlsanity.com/paper/2204.08824/) (2022)
- [LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modeling](https://mlsanity.com/paper/2208.08622/) (2022)
- [Learning without Forgetting for 3D Point Cloud Objects](https://mlsanity.com/paper/2106.14275/) (2021)
- [PSNet: Fast Data Structuring for Hierarchical Deep Learning on Point Cloud](https://mlsanity.com/paper/2205.14965/) (2022)
- [Keypoint Cascade Voting for Point Cloud Based 6DoF Pose Estimation](https://mlsanity.com/paper/2210.08123/) (2022)
- [Learning Mesh Representations via Binary Space Partitioning Tree Networks](https://mlsanity.com/paper/2106.14274/) (2021)
- [Transient Hemodynamics Prediction Using an Efficient Octree-Based Deep Learning Model](https://mlsanity.com/paper/2302.06557/) (2023)
- [Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data via Differentiable Cross-Approximation](https://mlsanity.com/paper/2105.14250/) (2021)

## 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.