Saved in:
Bibliographic Details
Main Authors: Herau, Quentin, Piasco, Nathan, Bennehar, Moussab, Roldão, Luis, Tsishkou, Dzmitry, Liu, Bingbing, Migniot, Cyrille, Vasseur, Pascal, Demonceaux, Cédric
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.15776
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908337153507328
author Herau, Quentin
Piasco, Nathan
Bennehar, Moussab
Roldão, Luis
Tsishkou, Dzmitry
Liu, Bingbing
Migniot, Cyrille
Vasseur, Pascal
Demonceaux, Cédric
author_facet Herau, Quentin
Piasco, Nathan
Bennehar, Moussab
Roldão, Luis
Tsishkou, Dzmitry
Liu, Bingbing
Migniot, Cyrille
Vasseur, Pascal
Demonceaux, Cédric
contents Autonomous driving systems rely on accurate perception and localization of the ego car to ensure safety and reliability in challenging real-world driving scenarios. Public datasets play a vital role in benchmarking and guiding advancement in research by providing standardized resources for model development and evaluation. However, potential inaccuracies in sensor calibration and vehicle poses within these datasets can lead to erroneous evaluations of downstream tasks, adversely impacting the reliability and performance of the autonomous systems. To address this challenge, we propose a robust optimization method based on Neural Radiance Fields (NeRF) to refine sensor poses and calibration parameters, enhancing the integrity of dataset benchmarks. To validate improvement in accuracy of our optimized poses without ground truth, we present a thorough evaluation process, relying on reprojection metrics, Novel View Synthesis rendering quality, and geometric alignment. We demonstrate that our method achieves significant improvements in sensor pose accuracy. By optimizing these critical parameters, our approach not only improves the utility of existing datasets but also paves the way for more reliable autonomous driving models. To foster continued progress in this field, we make the optimized sensor poses publicly available, providing a valuable resource for the research community.
format Preprint
id arxiv_https___arxiv_org_abs_2504_15776
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pose Optimization for Autonomous Driving Datasets using Neural Rendering Models
Herau, Quentin
Piasco, Nathan
Bennehar, Moussab
Roldão, Luis
Tsishkou, Dzmitry
Liu, Bingbing
Migniot, Cyrille
Vasseur, Pascal
Demonceaux, Cédric
Computer Vision and Pattern Recognition
Robotics
Autonomous driving systems rely on accurate perception and localization of the ego car to ensure safety and reliability in challenging real-world driving scenarios. Public datasets play a vital role in benchmarking and guiding advancement in research by providing standardized resources for model development and evaluation. However, potential inaccuracies in sensor calibration and vehicle poses within these datasets can lead to erroneous evaluations of downstream tasks, adversely impacting the reliability and performance of the autonomous systems. To address this challenge, we propose a robust optimization method based on Neural Radiance Fields (NeRF) to refine sensor poses and calibration parameters, enhancing the integrity of dataset benchmarks. To validate improvement in accuracy of our optimized poses without ground truth, we present a thorough evaluation process, relying on reprojection metrics, Novel View Synthesis rendering quality, and geometric alignment. We demonstrate that our method achieves significant improvements in sensor pose accuracy. By optimizing these critical parameters, our approach not only improves the utility of existing datasets but also paves the way for more reliable autonomous driving models. To foster continued progress in this field, we make the optimized sensor poses publicly available, providing a valuable resource for the research community.
title Pose Optimization for Autonomous Driving Datasets using Neural Rendering Models
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2504.15776