# Observation Quality in DSM-Assisted Aerial Localization: A Benchmark and Base-Anchored Uncertainty Calibration

arXiv: https://arxiv.org/abs/2610.18564 · HTML: https://mlsanity.com/paper/2610.18564/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 14 references that are in the map.
- First posted on arXiv 13 Oct 2026.

## Builds on (most cited first, 10 of 10)

- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [RoMa: Robust Dense Feature Matching](https://mlsanity.com/paper/2305.15404/) (2023)
- [Evaluating and Calibrating Uncertainty Prediction in Regression Tasks](https://mlsanity.com/paper/1905.11659/) (2019)
- [GIM: Learning Generalizable Image Matcher From Internet Videos](https://mlsanity.com/paper/2402.11095/) (2024)
- [Minimum Covariance Determinant and Extensions](https://mlsanity.com/paper/1709.07045/) (2017)
- [Uncertainty-Aware Camera Pose Estimation from Points and Lines](https://mlsanity.com/paper/2107.03890/) (2021)
- [OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata](https://mlsanity.com/paper/2509.18350/) (2025)
- [Parametric and Multivariate Uncertainty Calibration for Regression and Object Detection](https://mlsanity.com/paper/2207.01242/) (2022)
- [Reference-Induced Consensus for Selective Posed-Reference Visual Localization](https://mlsanity.com/paper/2607.04722/) (2026)

## Abstract (arXiv)

Aerial map matching provides position observations for navigation, but a position error alone does not determine how an observation should be weighted. We define five benchmark tasks: position availability and agreement, grouped error structure, predictive uncertainty, controlled updates, and temporal accumulation. A case study in digital-surface-model-assisted localization evaluates base-anchored uncertainty calibration within this framework. The method combines propagated image and map sensitivities with the second moment of a compact configuration subset relative to the reported position. The reported position remains unchanged, and scale is fitted using separate position references without local surface-height ground truth. Thirteen covariance models are evaluated on two held-out query sets from locations represented in the calibration data. Relative to a constant full-matrix baseline, the method reduces equal-location normalized position-update risk by 7.70% on 728 conditions and 5.46% on a separate 142 conditions under an independent prior, with all localization failures included. On the primary set, equal-location negative log likelihood improves by 2.571 nat. These results show improved reference-based weighting at seen locations. Exploratory base-quality and conditional-addition controls leave the incremental update benefit of configuration disagreement unresolved. Navigation benefit and real temporal accumulation remain untested.