# Recovering from Pose-Selection Failures in Repeated Visual Localization

arXiv: https://arxiv.org/abs/2610.16409 · HTML: https://mlsanity.com/paper/2610.16409/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 37 references that are in the map.
- First posted on arXiv 12 Oct 2026.

## Builds on (most cited first, 25 of 25)

- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018)
- [AnyLoc: Towards Universal Visual Place Recognition](https://mlsanity.com/paper/2308.00688/) (2023)
- [LaMAR: Benchmarking Localization and Mapping for Augmented Reality](https://mlsanity.com/paper/2210.10770/) (2022)
- [MegaLoc: One Retrieval to Place Them All](https://mlsanity.com/paper/2502.17237/) (2025)
- [SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition](https://mlsanity.com/paper/2102.11603/) (2021)
- [Are We Ready for Service Robots? The OpenLORIS-Scene Datasets for Lifelong SLAM](https://mlsanity.com/paper/1911.05603/) (2019)
- [DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers](https://mlsanity.com/paper/2503.14405/) (2025)
- [360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queries](https://mlsanity.com/paper/2311.17389/) (2023)
- [Large-scale Localization Datasets in Crowded Indoor Spaces](https://mlsanity.com/paper/2105.08941/) (2021)
- [Is This The Right Place? Geometric-Semantic Pose Verification for Indoor Visual Localization](https://mlsanity.com/paper/1908.04598/) (2019)
- [Intelligent Reference Curation for Visual Place Recognition via Bayesian Selective Fusion](https://mlsanity.com/paper/2010.09228/) (2020)
- [On the Estimation of Image-matching Uncertainty in Visual Place Recognition](https://mlsanity.com/paper/2404.00546/) (2024)
- [JIST: Joint Image and Sequence Training for Sequential Visual Place Recognition](https://mlsanity.com/paper/2403.19787/) (2024)
- [Improving Visual Place Recognition Based Robot Navigation By Verifying Localization Estimates](https://mlsanity.com/paper/2407.08162/) (2024)
- [Probabilistic Appearance-Invariant Topometric Localization with New Place Awareness](https://mlsanity.com/paper/2107.07707/) (2021)
- [Improving Visual Place Recognition with Sequence-Matching Receptiveness Prediction](https://mlsanity.com/paper/2503.06840/) (2025)
- [Combining Absolute and Semi-Generalized Relative Poses for Visual Localization](https://mlsanity.com/paper/2409.14269/) (2024)
- [Dynamically Modulating Visual Place Recognition Sequence Length For Minimum Acceptable Performance Scenarios](https://mlsanity.com/paper/2407.00863/) (2024)
- [Through the Lens of Doubt: Robust and Efficient Uncertainty Estimation for Visual Place Recognition](https://mlsanity.com/paper/2510.13464/) (2025)
- [Can You Trust Your Pose? Confidence Estimation in Visual Localization](https://mlsanity.com/paper/2010.00347/) (2020)
- [Quantile Transfer for Reliable Operating Point Selection in Visual Place Recognition](https://mlsanity.com/paper/2602.04401/) (2026)

## Abstract (arXiv)

Repetitive structures can give an incorrect pose candidate more inlier support than an accurate one, causing visual localization to select it. History-Guided Pose Reselection (HPR) uses coarse position forecasts from up to five past localization outputs to distinguish well-separated current-query candidates. The best-fitting forecast proposes an alternative; HPR accepts it only if every well-fitting forecast is much closer to it than to the localizer's pose. HPR needs no odometry and returns the selected candidate unchanged, using prediction for selection rather than pose refinement. With one development-set threshold, HPR improves recall within 5 meters and 10 degrees in all 12 main configurations of Hierarchical Localization (HLoc), MASt3R-based pose generation, and JIST-based retrieval, losing successes on fewer than 0.4 percent of queries. On NAVER Gangnam B1, HPR corrects 97 HLoc failures and loses six successes; gains persist within 0.25 meters and 2 degrees on all three HLoc test sets. Median HPR runtime on HLoc candidates is below one millisecond, excluding pose generation. Recovery weakens under less frequent localization.