# LatticeNet: Fast Point Cloud Segmentation Using Permutohedral Lattices

arXiv: https://arxiv.org/abs/1912.05905 · HTML: https://mlsanity.com/paper/1912.05905/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2019.

## Built on by (most cited first, 30 of 38)

- [(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network](https://mlsanity.com/paper/2102.04530/) (2021)
- [2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds](https://mlsanity.com/paper/2207.04397/) (2022)
- [Fast Point Transformer](https://mlsanity.com/paper/2112.04702/) (2021)
- [SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds](https://mlsanity.com/paper/2104.04891/) (2021)
- [Contrastive Boundary Learning for Point Cloud Segmentation](https://mlsanity.com/paper/2203.05272/) (2022)
- [Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2301.10100/) (2023)
- [Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling](https://mlsanity.com/paper/2107.02389/) (2021)
- [SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Clouds](https://mlsanity.com/paper/2201.04494/) (2022)
- [FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decoding](https://mlsanity.com/paper/2109.03787/) (2021)
- [ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenation](https://mlsanity.com/paper/2111.15242/) (2021)
- [Lite-HDSeg: LiDAR Semantic Segmentation Using Lite Harmonic Dense Convolutions](https://mlsanity.com/paper/2103.08852/) (2021)
- [Deep Learning Based 3D Segmentation: A Survey](https://mlsanity.com/paper/2103.05423/) (2021)
- [LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment](https://mlsanity.com/paper/2103.02263/) (2021)
- [DRINet++: Efficient Voxel-as-point Point Cloud Segmentation](https://mlsanity.com/paper/2111.08318/) (2021)
- [Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregation](https://mlsanity.com/paper/2202.13377/) (2022)
- [Scalable SoftGroup for 3D Instance Segmentation on Point Clouds](https://mlsanity.com/paper/2209.08263/) (2022)
- [COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation](https://mlsanity.com/paper/2210.01784/) (2022)
- [LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels](https://mlsanity.com/paper/2403.15173/) (2024)
- [TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2407.09751/) (2024)
- [LatticeNet: Fast Spatio-Temporal Point Cloud Segmentation Using Permutohedral Lattices](https://mlsanity.com/paper/2108.03917/) (2021)
- [S3Net: 3D LiDAR Sparse Semantic Segmentation Network](https://mlsanity.com/paper/2103.08745/) (2021)
- [Real-time Multi-Adaptive-Resolution-Surfel 6D LiDAR Odometry using Continuous-time Trajectory Optimization](https://mlsanity.com/paper/2105.02010/) (2021)
- [Abstract Flow for Temporal Semantic Segmentation on the Permutohedral Lattice](https://mlsanity.com/paper/2203.15469/) (2022)
- [Radar Instance Transformer: Reliable Moving Instance Segmentation in Sparse Radar Point Clouds](https://mlsanity.com/paper/2309.16435/) (2023)
- [A Review of Panoptic Segmentation for Mobile Mapping Point Clouds](https://mlsanity.com/paper/2304.13980/) (2023)
- [Unsupervised deep learning for semantic segmentation of multispectral LiDAR forest point clouds](https://mlsanity.com/paper/2502.06227/) (2025)
- [Efficient Urban-scale Point Clouds Segmentation with BEV Projection](https://mlsanity.com/paper/2109.09074/) (2021)
- [Sequential Point Clouds: A Survey](https://mlsanity.com/paper/2204.09337/) (2022)
- [Deep Learning on 3D Semantic Segmentation: A Detailed Review](https://mlsanity.com/paper/2411.02104/) (2024)
- [Knowledge Distillation from 3D to Bird's-Eye-View for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2304.11393/) (2023)

## Abstract (arXiv)

Deep convolutional neural networks (CNNs) have shown outstanding performance in the task of semantically segmenting images. However, applying the same methods on 3D data still poses challenges due to the heavy memory requirements and the lack of structured data. Here, we propose LatticeNet, a novel approach for 3D semantic segmentation, which takes as input raw point clouds. A PointNet describes the local geometry which we embed into a sparse permutohedral lattice. The lattice allows for fast convolutions while keeping a low memory footprint. Further, we introduce DeformSlice, a novel learned data-dependent interpolation for projecting lattice features back onto the point cloud. We present results of 3D segmentation on various datasets where our method achieves state-of-the-art performance.