Synthetic LiDAR Data Generation and Deterministic Downsampling for Point Cloud Classification on the Edge
Niclas Meyer, Stefan Reitmann
cs.LG, cs.RO
Submitted: 2026-08-07
Updated: 2026-08-10
Code: https://github.com/yanx27/Pointnet_Pointnet2_pytorch
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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
Terminology
Abstract
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.
Sources
- 3D ShapeNets: A Deep Representation for Volumetric Shapes
- Adaptive Hierarchical Down-Sampling for Point Cloud Classification
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
- Survey of Nearest Neighbor Techniques
- SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences
- Enhancing 3D Point Cloud Classification with ModelNet-R and Point-SkipNet
- Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey
- PointCutMix: Regularization Strategy for Point Cloud Classification
- Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions
- Virtual Sparse Convolution for Multimodal 3D Object Detection
- Deep Learning on 3D Semantic Segmentation: A Detailed Review
- Point Cloud Based Scene Segmentation: A Survey
- Point2Vec for Self-Supervised Representation Learning on Point Clouds
- SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud
- Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classification
- SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud
- PointCloud Saliency Maps
- Fast and Simple Explainability for Point Cloud Networks
- Surrogate Model-Based Explainability Methods for Point Cloud NNs
- 3D-MiniNet: Learning a 2D Representation from Point Clouds for Fast and Efficient 3D LIDAR Semantic Segmentation
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks