AI-Based Point Cloud Upsampling for Autonomous Driving Systems

Autonomous driving, decades ago relegated to the realm of science fiction, emerged as a tangible reality that is rapidly transforming the automotive industry, redefining our relationship with vehicles, and placing them in the spotlight of both the industry and the general public. Through the study...

Full description

Saved in:
Bibliographic Details
Main Authors: Nicolás Salomón, Claudio A. Delrieux, Damián A. Morero, Leandro E. Borgnino
Format: Article
Language:English
Published: Centro Latinoamericano de Estudios en Informática 2025-05-01
Series:CLEI Electronic Journal
Online Access:https://clei.org/cleiej/index.php/cleiej/article/view/811
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850138425969082368
author Nicolás Salomón
Claudio A. Delrieux
Damián A. Morero
Leandro E. Borgnino
author_facet Nicolás Salomón
Claudio A. Delrieux
Damián A. Morero
Leandro E. Borgnino
author_sort Nicolás Salomón
collection DOAJ
description Autonomous driving, decades ago relegated to the realm of science fiction, emerged as a tangible reality that is rapidly transforming the automotive industry, redefining our relationship with vehicles, and placing them in the spotlight of both the industry and the general public. Through the study and analysis of modern and efficient interpolation techniques, we aim to reduce the current costs and processing requirements associated with the LiDAR sensor, which is one of the main information sources. Our approach explores the fusion of lower-cost LiDAR sensors with advanced interpolation techniques, with a particular focus on achieving performance parity with pricier 64-channel LiDAR setups. This work is based on 3 main axes: firstly, the analysis of available LiDAR data and its representation; secondly, the development and implementation of an interpolation technique based on 1D convolutional layers integrated with fully connected layers, in order to analyse data coming from a sliding window; and finally, the comparative evaluation of the results between different state-of-the-art interpolation techniques, using object detection networks in point clouds. Furthermore, a basic analysis regarding power consumption and a potential hardware implementation is presented. By interpolating the point clouds with the proposed technique, improvements between 1.92% and 30.98% in detection and classification tasks were achieved, depending on the object and the type of detection (3D or bird's eye view). Furthermore, computational efficiency was not left aside by reducing the inference times necessary for interpolation, compared to other techniques used as contrast. This highlights the viability and scalability of our approach in realizing cost-effective yet high-performance autonomous driving systems.
format Article
id doaj-art-762167a5007b4300937e758d95cee08a
institution OA Journals
issn 0717-5000
language English
publishDate 2025-05-01
publisher Centro Latinoamericano de Estudios en Informática
record_format Article
series CLEI Electronic Journal
spelling doaj-art-762167a5007b4300937e758d95cee08a2025-08-20T02:30:35ZengCentro Latinoamericano de Estudios en InformáticaCLEI Electronic Journal0717-50002025-05-0128310.19153/cleiej.28.3.3AI-Based Point Cloud Upsampling for Autonomous Driving SystemsNicolás Salomón0Claudio A. Delrieux1Damián A. Morero2Leandro E. Borgnino3Fundación Fulgor / UNSDepartamento de Ingeniería Eléctrica y Computadoras, Universidad Nacional del Sur Laboratorio de Comunicaciones Digitales, Universidad Nacional de CórdobaDepartamento de Electrónica, Universidad Nacional de Córdoba Autonomous driving, decades ago relegated to the realm of science fiction, emerged as a tangible reality that is rapidly transforming the automotive industry, redefining our relationship with vehicles, and placing them in the spotlight of both the industry and the general public. Through the study and analysis of modern and efficient interpolation techniques, we aim to reduce the current costs and processing requirements associated with the LiDAR sensor, which is one of the main information sources. Our approach explores the fusion of lower-cost LiDAR sensors with advanced interpolation techniques, with a particular focus on achieving performance parity with pricier 64-channel LiDAR setups. This work is based on 3 main axes: firstly, the analysis of available LiDAR data and its representation; secondly, the development and implementation of an interpolation technique based on 1D convolutional layers integrated with fully connected layers, in order to analyse data coming from a sliding window; and finally, the comparative evaluation of the results between different state-of-the-art interpolation techniques, using object detection networks in point clouds. Furthermore, a basic analysis regarding power consumption and a potential hardware implementation is presented. By interpolating the point clouds with the proposed technique, improvements between 1.92% and 30.98% in detection and classification tasks were achieved, depending on the object and the type of detection (3D or bird's eye view). Furthermore, computational efficiency was not left aside by reducing the inference times necessary for interpolation, compared to other techniques used as contrast. This highlights the viability and scalability of our approach in realizing cost-effective yet high-performance autonomous driving systems. https://clei.org/cleiej/index.php/cleiej/article/view/811
spellingShingle Nicolás Salomón
Claudio A. Delrieux
Damián A. Morero
Leandro E. Borgnino
AI-Based Point Cloud Upsampling for Autonomous Driving Systems
CLEI Electronic Journal
title AI-Based Point Cloud Upsampling for Autonomous Driving Systems
title_full AI-Based Point Cloud Upsampling for Autonomous Driving Systems
title_fullStr AI-Based Point Cloud Upsampling for Autonomous Driving Systems
title_full_unstemmed AI-Based Point Cloud Upsampling for Autonomous Driving Systems
title_short AI-Based Point Cloud Upsampling for Autonomous Driving Systems
title_sort ai based point cloud upsampling for autonomous driving systems
url https://clei.org/cleiej/index.php/cleiej/article/view/811
work_keys_str_mv AT nicolassalomon aibasedpointcloudupsamplingforautonomousdrivingsystems
AT claudioadelrieux aibasedpointcloudupsamplingforautonomousdrivingsystems
AT damianamorero aibasedpointcloudupsamplingforautonomousdrivingsystems
AT leandroeborgnino aibasedpointcloudupsamplingforautonomousdrivingsystems