# OctNet: Learning Deep 3D Representations at High Resolutions

arXiv: https://arxiv.org/abs/1611.05009 · HTML: https://mlsanity.com/paper/1611.05009/

## Key facts

- Cited by 342 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2016.

## Built on by (most cited first, 30 of 342)

- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [PlenOctrees for Real-time Rendering of Neural Radiance Fields](https://mlsanity.com/paper/2103.14024/) (2021)
- [Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis](https://mlsanity.com/paper/2111.04276/) (2021)
- [3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models](https://mlsanity.com/paper/2301.11445/) (2023)
- [Advances in Neural Rendering](https://mlsanity.com/paper/2111.05849/) (2021)
- [An End-to-End Transformer Model for 3D Object Detection](https://mlsanity.com/paper/2109.08141/) (2021)
- [Language-Grounded Indoor 3D Semantic Segmentation in the Wild](https://mlsanity.com/paper/2204.07761/) (2022)
- [Self-Supervised Pretraining of 3D Features on any Point-Cloud](https://mlsanity.com/paper/2101.02691/) (2021)
- [PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds](https://mlsanity.com/paper/2103.14635/) (2021)
- [SoftGroup for 3D Instance Segmentation on Point Clouds](https://mlsanity.com/paper/2203.01509/) (2022)
- [Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning](https://mlsanity.com/paper/2403.11401/) (2024)
- [RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation](https://mlsanity.com/paper/2103.12978/) (2021)
- [Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis](https://mlsanity.com/paper/2105.01288/) (2021)
- [Deep Parametric Continuous Convolutional Neural Networks](https://mlsanity.com/paper/2101.06742/) (2021)
- [InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring](https://mlsanity.com/paper/2103.01128/) (2021)
- [Hierarchical Aggregation for 3D Instance Segmentation](https://mlsanity.com/paper/2108.02350/) (2021)
- [NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes](https://mlsanity.com/paper/2111.13260/) (2021)
- [A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation](https://mlsanity.com/paper/2104.07645/) (2021)
- [OctFormer: Octree-based Transformers for 3D Point Clouds](https://mlsanity.com/paper/2305.03045/) (2023)
- [Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks](https://mlsanity.com/paper/2103.10429/) (2021)
- [DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models](https://mlsanity.com/paper/2402.19481/) (2024)
- [Bidirectional Projection Network for Cross Dimension Scene Understanding](https://mlsanity.com/paper/2103.14326/) (2021)
- [3DILG: Irregular Latent Grids for 3D Generative Modeling](https://mlsanity.com/paper/2205.13914/) (2022)
- [POCO: Point Convolution for Surface Reconstruction](https://mlsanity.com/paper/2201.01831/) (2022)
- [One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation](https://mlsanity.com/paper/2104.02246/) (2021)
- [Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2110.08188/) (2021)
- [A comprehensive survey on point cloud registration](https://mlsanity.com/paper/2103.02690/) (2021)
- [Surface Representation for Point Clouds](https://mlsanity.com/paper/2205.05740/) (2022)
- [3D Semantic Scene Completion: a Survey](https://mlsanity.com/paper/2103.07466/) (2021)
- [P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting](https://mlsanity.com/paper/2208.02812/) (2022)

## Abstract (arXiv)

We present OctNet, a representation for deep learning with sparse 3D data. In contrast to existing models, our representation enables 3D convolutional networks which are both deep and high resolution. Towards this goal, we exploit the sparsity in the input data to hierarchically partition the space using a set of unbalanced octrees where each leaf node stores a pooled feature representation. This allows to focus memory allocation and computation to the relevant dense regions and enables deeper networks without compromising resolution. We demonstrate the utility of our OctNet representation by analyzing the impact of resolution on several 3D tasks including 3D object classification, orientation estimation and point cloud labeling.