Uncertainty-Aware Online Extrinsic Calibration: A Conformal Prediction Approach

Abstract

Accurate sensor calibration is crucial for autonomous systems, yet uncertainty quantification for online extrinsic calibration remains underexplored. We present the first approach to integrate uncertainty awareness into online extrinsic calibration, combining Monte Carlo Dropout with Conformal Prediction to generate prediction intervals with guaranteed coverage.

Our framework augments existing calibration models with architecture-agnostic uncertainty quantification. Validated on KITTI (RGB Camera–LiDAR) and DSEC (Event Camera–LiDAR), we evaluate interval efficiency and reliability with adapted metrics across both sensor types.

Calibration outputs include explicit uncertainty intervals, so downstream fusion can weight or reject misaligned sensor pairs instead of treating every estimate as equally trustworthy.

Key Contributions

• First application of conformal prediction to sensor calibration with coverage guarantees
• Uncertainty quantification for extrinsic calibration parameters via Monte Carlo Dropout
• Improved generalization on out-of-distribution data
• Performance gains on downstream odometry
• Framework compatible with existing calibration network architectures

Citation

@InProceedings{Cocheteux_2025_WACV,
    author    = {Cocheteux, Mathieu and Moreau, Julien and Davoine, Franck},
    title     = {Uncertainty-Aware Online Extrinsic Calibration: A Conformal Prediction Approach},
    booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)},
    month     = {February},
    year      = {2025},
    pages     = {6167-6176}
}