# Analyzing Deep Learning Representations of Point Clouds for Real-Time In-Vehicle LiDAR Perception

arXiv: https://arxiv.org/abs/2210.14612 · HTML: https://mlsanity.com/paper/2210.14612/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 41 references that are in the map.
- First posted on arXiv 26 Oct 2022.

## Builds on (most cited first, 29 of 29)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://mlsanity.com/paper/1911.11236/) (2019)
- [Deep Learning for 3D Point Clouds: A Survey](https://mlsanity.com/paper/1912.12033/) (2019)
- [Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution](https://mlsanity.com/paper/2007.16100/) (2020)
- [A Survey of Autonomous Driving: Common Practices and Emerging Technologies](https://mlsanity.com/paper/1906.05113/) (2019)
- [Point-Voxel CNN for Efficient 3D Deep Learning](https://mlsanity.com/paper/1907.03739/) (2019)
- [PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation](https://mlsanity.com/paper/2003.14032/) (2020)
- [SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud](https://mlsanity.com/paper/1809.08495/) (2018)
- [SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving](https://mlsanity.com/paper/2003.03653/) (2020)
- [Tangent Convolutions for Dense Prediction in 3D](https://mlsanity.com/paper/1807.02443/) (2018)
- [RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation](https://mlsanity.com/paper/2103.12978/) (2021)
- [SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation](https://mlsanity.com/paper/2004.01803/) (2020)
- [Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2206.02099/) (2022)
- [Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation](https://mlsanity.com/paper/2008.01550/) (2020)
- [3D Object Detection for Autonomous Driving: A Survey](https://mlsanity.com/paper/2106.10823/) (2021)
- [Bag of Freebies for Training Object Detection Neural Networks](https://mlsanity.com/paper/1902.04103/) (2019)
- [Lite-HDSeg: LiDAR Semantic Segmentation Using Lite Harmonic Dense Convolutions](https://mlsanity.com/paper/2103.08852/) (2021)
- [Scan-based Semantic Segmentation of LiDAR Point Clouds: An Experimental Study](https://mlsanity.com/paper/2004.11803/) (2020)
- [Transformers in 3D Point Clouds: A Survey](https://mlsanity.com/paper/2205.07417/) (2022)
- [LIBRE: The Multiple 3D LiDAR Dataset](https://mlsanity.com/paper/2003.06129/) (2020)
- [PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution](https://mlsanity.com/paper/2204.11797/) (2022)
- [CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentation](https://mlsanity.com/paper/2204.09914/) (2022)
- [Accurate, Low-Latency Visual Perception for Autonomous Racing:Challenges, Mechanisms, and Practical Solutions](https://mlsanity.com/paper/2007.13971/) (2020)
- [Semi-Local Convolutions for LiDAR Scan Processing](https://mlsanity.com/paper/2111.15615/) (2021)

## Built on by (most cited first, 8 of 8)

- [Rethinking Range View Representation for LiDAR Segmentation](https://mlsanity.com/paper/2303.05367/) (2023)
- [Segment Any Point Cloud Sequences by Distilling Vision Foundation Models](https://mlsanity.com/paper/2306.09347/) (2023)
- [4D Contrastive Superflows are Dense 3D Representation Learners](https://mlsanity.com/paper/2407.06190/) (2024)
- [TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR Semantic Segmentation](https://mlsanity.com/paper/2309.07849/) (2023)
- [An Empirical Study of Training State-of-the-Art LiDAR Segmentation Models](https://mlsanity.com/paper/2405.14870/) (2024)
- [LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving](https://mlsanity.com/paper/2501.04005/) (2025)
- [Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding](https://mlsanity.com/paper/2403.17010/) (2024)
- [From One to the Power of Many: Invariance to Multi-LiDAR Perception from Single-Sensor Datasets](https://mlsanity.com/paper/2409.18592/) (2024)

## Abstract (arXiv)

LiDAR sensors are an integral part of modern autonomous vehicles as they provide an accurate, high-resolution 3D representation of the vehicle's surroundings. However, it is computationally difficult to make use of the ever-increasing amounts of data from multiple high-resolution LiDAR sensors. As frame-rates, point cloud sizes and sensor resolutions increase, real-time processing of these point clouds must still extract semantics from this increasingly precise picture of the vehicle's environment. One deciding factor of the run-time performance and accuracy of deep neural networks operating on these point clouds is the underlying data representation and the way it is computed. In this work, we examine the relationship between the computational representations used in neural networks and their performance characteristics. To this end, we propose a novel computational taxonomy of LiDAR point cloud representations used in modern deep neural networks for 3D point cloud processing. Using this taxonomy, we perform a structured analysis of different families of approaches. Thereby, we uncover common advantages and limitations in terms of computational efficiency, memory requirements, and representational capacity as measured by semantic segmentation performance. Finally, we provide some insights and guidance for future developments in neural point cloud processing methods.