Metraipolis › archive › dc_604aece9f479

Topometric Autonomous Vehicle Localization by Combining Visual Embeddings and Feed-Forward 3D Models — arXiv:2608.06021

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.06021
License (as archived)
CC0-1.0
Archived
2026-10-31T10:38:20.115Z
SHA-256 of the archived text
6550690a991d8fa0518016a8fa71fd20ce90eaef9db90b595c8601c43f827eac
Stable URL of this page
https://metraipolis.com/documento/dc_604aece9f479

How to cite

Topometric Autonomous Vehicle Localization by Combining Visual Embeddings and Feed-Forward 3D Models — arXiv:2608.06021 — arXiv (en), https://arxiv.org/abs/2608.06021 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_604aece9f479 (Metraipolis archive dc_604aece9f479, sha256 6550690a991d8fa0518016a8fa71fd20ce90eaef9db90b595c8601c43f827eac)
BibTeX
@misc{dc604aece9f479,
  title = {Topometric Autonomous Vehicle Localization by Combining Visual Embeddings and Feed-Forward 3D Models — arXiv:2608.06021},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.06021},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_604aece9f479; sha256 6550690a991d8fa0518016a8fa71fd20ce90eaef9db90b595c8601c43f827eac},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06021. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Effective Visual Localization (VL) requires a map of the environment that combines compactness for efficient scalability with robustness against visual appearance changes and metric precision. Through low-dimensional image embeddings, Visual Place Recognition (VPR) is able to successfully meet the first two requirements, but its low metric accuracy makes it less suitable than standard VL approaches based on local features or neural representations. This limitation can be overcome by integrating VPR with the accurate local trajectory estimates produced by feed-forward neural 3D geometry (FF3D) models. In this paper, we address sequential appearance-based localization through a topometric framework that iteratively combines probabilistic VPR with FF3D metric pose estimation in controlled image sets. Our approach proposes an automatic offline mapping tool that models the topometric pose-appearance interaction in the different parts of the scene. This map is later employed by an online particle filter that estimates the pose from odometry and belief over places for FF3D inference, successfully incorporating neural metric estimation into probabilistic appearance-based localization. We extensively evaluate the framework on three known benchmarks, demonstrating substantial improvements over existing appearance-based methods. The modularity of our approach allows the descriptor extractor and FF3D model to remain interchangeable, and a focused analysis further shows that sequential belief can mitigate severe failures under perceptual aliasing.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.06021 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T10:24:02.123Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).