Abstract
This PhD thesis presents novel deep learning approaches for robust multi-sensor calibration in autonomous driving systems. The work introduces uncertainty-aware calibration methods and demonstrates their effectiveness in real-world scenarios.
The research focuses on developing practical solutions for sensor calibration challenges in autonomous vehicles, with particular emphasis on LiDAR-camera perception and uncertainty estimation. The thesis contributes to the field through publications in top-tier conferences and an international patent.
Defended in April 2025 at the Université de technologie de Compiègne, under the supervision of Julien Moreau and Franck Davoine at the Heudiasyc Laboratory.
Key Contributions
- Uncertainty-aware calibration: first approach integrating conformal prediction into online extrinsic calibration with guaranteed coverage intervals
- Initialization-free calibration: PseudoCal — first deep learning method for camera-LiDAR calibration without manual initialization, operating directly in 3D space
- LiDAR-event camera calibration: MULi-Ev — first online framework for extrinsic calibration of event cameras with LiDAR
- Transformer-based architecture: UniCal — efficient single-branch model for simultaneous calibration and validation, leading to an international patent
- Real-world validation: methods evaluated on autonomous driving datasets including KITTI, DSEC, and nuScenes
Publications from this Thesis
- WACV 2025 Uncertainty-Aware Online Extrinsic Calibration: A Conformal Prediction Approach — Read more →
- CVPR 2024 MULi-Ev: Maintaining Unperturbed LiDAR-Event Calibration — Read more →
- BMVC 2023 PseudoCal: Towards Initialization-Free Camera-LiDAR Calibration — Read more →
- Patent UniCal: A Single-Branch Transformer-Based Model for Camera-to-LiDAR Calibration — Read more →
Citation
BibTeX
@phdthesis{cocheteux2025thesis,
author = {Cocheteux, Mathieu},
title = {Deep Learning for Multi-Sensor Calibration
in Autonomous Driving},
school = {Université de technologie de Compiègne},
year = {2025},
type = {PhD Thesis},
url = {https://theses.hal.science/tel-05268827v1}
}