# 3D Point Cloud Object Detection on Edge Devices for Split Computing

arXiv: https://arxiv.org/abs/2511.02293 · HTML: https://mlsanity.com/paper/2511.02293/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 4 Nov 2025.

## Builds on (most cited first, 7 of 7)

- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection](https://mlsanity.com/paper/2012.15712/) (2020)
- [Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges](https://mlsanity.com/paper/2103.04505/) (2021)
- [M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers](https://mlsanity.com/paper/2104.11896/) (2021)
- [BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split Computing](https://mlsanity.com/paper/2201.02693/) (2022)

## Built on by (most cited first, 1 of 1)

- [SC-MII: Infrastructure LiDAR-based 3D Object Detection on Edge Devices for Split Computing with Multiple Intermediate Outputs Integration](https://mlsanity.com/paper/2601.07119/) (2026)

## Abstract (arXiv)

The field of autonomous driving technology is rapidly advancing, with deep learning being a key component. Particularly in the field of sensing, 3D point cloud data collected by LiDAR is utilized to run deep neural network models for 3D object detection. However, these state-of-the-art models are complex, leading to longer processing times and increased power consumption on edge devices. The objective of this study is to address these issues by leveraging Split Computing, a distributed machine learning inference method. Split Computing aims to lessen the computational burden on edge devices, thereby reducing processing time and power consumption. Furthermore, it minimizes the risk of data breaches by only transmitting intermediate data from the deep neural network model. Experimental results show that splitting after voxelization reduces the inference time by 70.8% and the edge device execution time by 90.0%. When splitting within the network, the inference time is reduced by up to 57.1%, and the edge device execution time is reduced by up to 69.5%.