English

Query2Uncertainty: Robust Uncertainty Quantification and Calibration for 3D Object Detection under Distribution Shift

Computer Vision and Pattern Recognition 2026-05-08 v1 Robotics

Abstract

Reliable uncertainty estimation for 3D object detection is critical for deploying safe autonomous systems, yet modern detectors remain poorly calibrated, especially under distribution shifts. Although post-hoc calibration methods address this issue and provide improved calibration for in-distribution tests, they fail to adapt in distribution-shifted scenarios. In this work, we address this issue and introduce a density-aware calibration method that couples post-hoc calibrators with the feature density of latent object queries from DETR-style 3D object detectors. These queries form a compact, location and class-aware feature, ideal for density estimation, allowing our approach to adjust model confidences in distribution-shift scenarios. By fitting a density estimator on these query features, our approach jointly recalibrates both classification and bounding box regression uncertainties. On both a multi-view camera and LiDAR-based detector, our approach consistently outperforms standard post-hoc methods in both in-distribution and distribution-shifted scenarios. Code available https://tillbeemelmanns.github.io/query2uncertainty/ .

Keywords

Cite

@article{arxiv.2605.05328,
  title  = {Query2Uncertainty: Robust Uncertainty Quantification and Calibration for 3D Object Detection under Distribution Shift},
  author = {Till Beemelmanns and Alexey Nekrasov and Stefan Vilceanu and Jonas Steinhaus and Timo Woopen and Bastian Leibe and Lutz Eckstein},
  journal= {arXiv preprint arXiv:2605.05328},
  year   = {2026}
}

Comments

Accepted for publication at CVPR 2026

R2 v1 2026-07-01T12:53:30.279Z