# Synthetic LiDAR Data Generation and Deterministic Downsampling for Point Cloud Classification on the Edge

arXiv: https://arxiv.org/abs/2608.07106 · HTML: https://mlsanity.com/paper/2608.07106/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Builds on (most cited first, 24 of 24)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution](https://mlsanity.com/paper/2007.16100/) (2020)
- [SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud](https://mlsanity.com/paper/1710.07368/) (2017)
- [SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud](https://mlsanity.com/paper/1809.08495/) (2018)
- [PointCloud Saliency Maps](https://mlsanity.com/paper/1812.01687/) (2018)
- [Lidar for Autonomous Driving: The principles, challenges, and trends for automotive lidar and perception systems](https://mlsanity.com/paper/2004.08467/) (2020)
- [Virtual Sparse Convolution for Multimodal 3D Object Detection](https://mlsanity.com/paper/2303.02314/) (2023)
- [Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions](https://mlsanity.com/paper/2201.12296/) (2022)
- [PointCutMix: Regularization Strategy for Point Cloud Classification](https://mlsanity.com/paper/2101.01461/) (2021)
- [3D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation](https://mlsanity.com/paper/2002.10893/) (2020)
- [Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling](https://mlsanity.com/paper/2107.02389/) (2021)
- [Adaptive Hierarchical Down-Sampling for Point Cloud Classification](https://mlsanity.com/paper/1904.08506/) (2019)
- [Point2Vec for Self-Supervised Representation Learning on Point Clouds](https://mlsanity.com/paper/2303.16570/) (2023)
- [Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlook](https://mlsanity.com/paper/2311.02608/) (2023)
- [Surrogate Model-Based Explainability Methods for Point Cloud NNs](https://mlsanity.com/paper/2107.13459/) (2021)
- [Visualizing Global Explanations of Point Cloud DNNs](https://mlsanity.com/paper/2203.09505/) (2022)
- [Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classification](https://mlsanity.com/paper/2412.03056/) (2024)
- [Fast and Simple Explainability for Point Cloud Networks](https://mlsanity.com/paper/2403.07706/) (2024)
- [Deep Learning on 3D Semantic Segmentation: A Detailed Review](https://mlsanity.com/paper/2411.02104/) (2024)
- [Enhancing 3D Point Cloud Classification with ModelNet-R and Point-SkipNet](https://mlsanity.com/paper/2509.05198/) (2025)
- [Point Cloud Based Scene Segmentation: A Survey](https://mlsanity.com/paper/2503.12595/) (2025)

## Abstract (arXiv)

Deploying three-dimensional deep learning frameworks to low-power embedded processors is bottlenecked by the unstructured nature of spatial data and the resource-intensive distance sorting algorithms often used before neural network inference. To address this gap, this paper presents a hardware-constrained workflow optimized for native execution on the Raspberry Pi 5. To account for the reality gap between noiseless, clean computer-aided design (CAD) datasets and real-world sensor data, we use physics-based simulation to construct a synthetic LiDAR dataset. Cross-dataset evaluations demonstrate a substantial drop in classification accuracy when networks trained on clean CAD data are evaluated on synthetic LiDAR sensor data, highlighting the critical need for sensor-aware training. To address the latency bottleneck of traditional geometric preprocessing on edge CPUs, we integrate an isolated, feature-driven Critical Points Layer (CPL) as a frontend filter. Our results show that the pretrained CPL deterministically compresses raw 1024-point clouds to a subset of 40 to 60 unique coordinates. When profiled on the ARM Cortex-A76 processor, the complete pipeline achieves an inference throughput of approximately 50 FPS while maintaining an instance classification accuracy of 88.36%, demonstrating the viability of deterministic real-time 3D perception at the edge.