# Multi Projection Fusion for Real-time Semantic Segmentation of 3D LiDAR Point Clouds

arXiv: https://arxiv.org/abs/2011.01974 · HTML: https://mlsanity.com/paper/2011.01974/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Nov 2020.

## Built on by (most cited first, 24 of 24)

- [Rethinking Range View Representation for LiDAR Segmentation](https://mlsanity.com/paper/2303.05367/) (2023)
- [Scribble-Supervised LiDAR Semantic Segmentation](https://mlsanity.com/paper/2203.08537/) (2022)
- [CENet: Toward Concise and Efficient LiDAR Semantic Segmentation for Autonomous Driving](https://mlsanity.com/paper/2207.12691/) (2022)
- [FRNet: Frustum-Range Networks for Scalable LiDAR Segmentation](https://mlsanity.com/paper/2312.04484/) (2023)
- [FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decoding](https://mlsanity.com/paper/2109.03787/) (2021)
- [LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds](https://mlsanity.com/paper/2210.08064/) (2022)
- [GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2207.02605/) (2022)
- [Frame Mining: a Free Lunch for Learning Robotic Manipulation from 3D Point Clouds](https://mlsanity.com/paper/2210.07442/) (2022)
- [S4C: Self-Supervised Semantic Scene Completion with Neural Fields](https://mlsanity.com/paper/2310.07522/) (2023)
- [Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2308.12113/) (2023)
- [CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentation](https://mlsanity.com/paper/2204.09914/) (2022)
- [Center Focusing Network for Real-Time LiDAR Panoptic Segmentation](https://mlsanity.com/paper/2311.09499/) (2023)
- [Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2311.17491/) (2023)
- [Deep Learning on 3D Semantic Segmentation: A Detailed Review](https://mlsanity.com/paper/2411.02104/) (2024)
- [MVP-Net: Multiple View Pointwise Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/2201.12769/) (2022)
- [FLARES: Fast and Accurate LiDAR Multi-Range Semantic Segmentation](https://mlsanity.com/paper/2502.09274/) (2025)
- [Multi-to-Single Knowledge Distillation for Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2304.14800/) (2023)
- [TE-NeXt: A LiDAR-Based 3D Sparse Convolutional Network for Traversability Estimation](https://mlsanity.com/paper/2406.01395/) (2024)
- [Towards Explicit Geometry-Reflectance Collaboration for Generalized LiDAR Segmentation in Adverse Weather](https://mlsanity.com/paper/2506.02396/) (2025)
- [Point Cloud Segmentation Using Sparse Temporal Local Attention](https://mlsanity.com/paper/2112.00289/) (2021)
- [Lidar Annotation Is All You Need](https://mlsanity.com/paper/2311.04777/) (2023)
- [Improved LiDAR Odometry and Mapping using Deep Semantic Segmentation and Novel Outliers Detection](https://mlsanity.com/paper/2403.03111/) (2024)
- [RangeSAM: On the Potential of Visual Foundation Models for Range-View represented LiDAR segmentation](https://mlsanity.com/paper/2509.15886/) (2025)
- [From Spherical to Gaussian: A Comparative Analysis of Point Cloud Cropping Strategies in Large-Scale 3D Environments](https://mlsanity.com/paper/2605.02098/) (2026)

## Abstract (arXiv)

Semantic segmentation of 3D point cloud data is essential for enhanced high-level perception in autonomous platforms. Furthermore, given the increasing deployment of LiDAR sensors onboard of cars and drones, a special emphasis is also placed on non-computationally intensive algorithms that operate on mobile GPUs. Previous efficient state-of-the-art methods relied on 2D spherical projection of point clouds as input for 2D fully convolutional neural networks to balance the accuracy-speed trade-off. This paper introduces a novel approach for 3D point cloud semantic segmentation that exploits multiple projections of the point cloud to mitigate the loss of information inherent in single projection methods. Our Multi-Projection Fusion (MPF) framework analyzes spherical and bird's-eye view projections using two separate highly-efficient 2D fully convolutional models then combines the segmentation results of both views. The proposed framework is validated on the SemanticKITTI dataset where it achieved a mIoU of 55.5 which is higher than state-of-the-art projection-based methods RangeNet++ and PolarNet while being 1.6x faster than the former and 3.1x faster than the latter.