Related papers: Synthetic LiDAR Data Generation and Deterministic Downsampling for Point Cloud Classification on the Edge

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

URL: http://arxiv.org/abs/2608.07106v1
Date: Fri, 07 Aug 2026 11:02:55 GMT
Title: Synthetic LiDAR Data Generation and Deterministic Downsampling for Point Cloud Classification on the Edge
Abstract summary: This paper presents a hardware-constrained workflow optimized for native execution on the Raspberry Pi 5.6%.<n>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.<n>Cross-dataset evaluations demonstrate a substantial drop in classification accuracy when networks trained on clean CAD data are evaluated on synthetic LiDAR sensor data.
Score: 0.0
License: http://creativecommons.org/licenses/by/4.0/
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.

Related papers

Deep Learning-Based Early-Stage IR-Drop Estimation via CNN Surrogate Modeling [0.0]
Conventional IR-drop analysis relies on physics-based signoff tools, which provide high accuracy but incur significant computational cost.<n>We propose a deep learning-based surrogate modeling approach for early-stage IR-drop estimation using a CNN.<n>The proposed framework is intended as a complementary early-stage analysis tool, providing designers with rapid IR-drop insight prior to expensive signoff analysis.
arXiv Detail & Related papers (2026-01-30T08:29:45Z)
No One-Model-Fits-All: Uncovering Spatio-Temporal Forecasting Trade-offs with Graph Neural Networks and Foundation Models [8.918505166222875]
This work presents a systematic study of forecasting models under varying spatial sensor density and sampling intervals.<n>Our results show that STGs are effective when sensor deployments are sparse and sampling rate is moderate.<n> Crucially, TSFM performs competitively at high frequencies but degrades when spatial coverage from neighboring sensors is reduced.
arXiv Detail & Related papers (2025-11-07T11:50:39Z)
Private Training & Data Generation by Clustering Embeddings [74.00687214400021]
Differential privacy (DP) provides a robust framework for protecting individual data.<n>We introduce a novel principled method for DP synthetic image embedding generation.<n> Empirically, a simple two-layer neural network trained on synthetically generated embeddings achieves state-of-the-art (SOTA) classification accuracy.
arXiv Detail & Related papers (2025-06-20T00:17:14Z)
Are We Ready for Real-Time LiDAR Semantic Segmentation in Autonomous Driving? [42.348499880894686]
Scene semantic segmentation can be achieved by directly integrating 3D spatial data with specialized deep neural networks. We investigate various 3D semantic segmentation methodologies and analyze their performance and capabilities for resource-constrained inference on embedded NVIDIA Jetson platforms.
arXiv Detail & Related papers (2024-10-10T20:47:33Z)
OPUS: Occupancy Prediction Using a Sparse Set [64.60854562502523]
We present a framework to simultaneously predict occupied locations and classes using a set of learnable queries. OPUS incorporates a suite of non-trivial strategies to enhance model performance. Our lightest model achieves superior RayIoU on the Occ3D-nuScenes dataset at near 2x FPS, while our heaviest model surpasses previous best results by 6.1 RayIoU.
arXiv Detail & Related papers (2024-09-14T07:44:22Z)
PU-Ray: Domain-Independent Point Cloud Upsampling via Ray Marching on Neural Implicit Surface [5.78575346449322]
We propose a new ray-based upsampling approach with an arbitrary rate, where a depth prediction is made for each query ray and its corresponding patch. Our novel method simulates the sphere-tracing ray marching algorithm on the neural implicit surface defined with an unsigned distance function (UDF) The rule-based mid-point query sampling method generates more evenly distributed points without requiring an end-to-end model trained using a nearest-neighbor-based reconstruction loss function.
arXiv Detail & Related papers (2023-10-12T22:45:03Z)
AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration [69.21282992341007]
Auto Synth automatically generates 3D training data for point cloud registration. We replace the point cloud registration network with a much smaller surrogate network, leading to a $4056.43$ speedup. Our results on TUD-L, LINEMOD and Occluded-LINEMOD evidence that a neural network trained on our searched dataset yields consistently better performance than the same one trained on the widely used ModelNet40 dataset.
arXiv Detail & Related papers (2023-09-20T09:29:44Z)
V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection [73.37781484123536]
We introduce a highly performant 3D object detector for point clouds using the DETR framework. To address the limitation, we introduce a novel 3D Relative Position (3DV-RPE) method. We show exceptional results on the challenging ScanNetV2 benchmark.
arXiv Detail & Related papers (2023-08-08T17:14:14Z)
NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction [79.13750275141139]
This paper proposes a novel and fast self-supervised solution for sparse-view CBCT reconstruction. The desired attenuation coefficients are represented as a continuous function of 3D spatial coordinates, parameterized by a fully-connected deep neural network. A learning-based encoder entailing hash coding is adopted to help the network capture high-frequency details.
arXiv Detail & Related papers (2022-09-29T04:06:00Z)
D3DLO: Deep 3D LiDAR Odometry [1.1172382217477126]
LiDAR odometry (LO) describes the task of finding an alignment of subsequent LiDAR point clouds. This alignment can be used to estimate the motion of the platform where the LiDAR sensor is mounted on. We propose a network architecture that learns LO by directly processing 3D point clouds.
arXiv Detail & Related papers (2021-01-28T19:23:06Z)
ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation [111.56730703473411]
Training deep neural networks (DNNs) on LiDAR data requires large-scale point-wise annotations. Simulation-to-real domain adaptation (SRDA) trains a DNN using unlimited synthetic data with automatically generated labels. ePointDA consists of three modules: self-supervised dropout noise rendering, statistics-invariant and spatially-adaptive feature alignment, and transferable segmentation learning.
arXiv Detail & Related papers (2020-09-07T23:46:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.