GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Khatib, Fadi, Moran, Dror, Trostianetsky, Guy, Kasten, Yoni, Galun, Meirav, Basri, Ronen
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908502334636032
author Khatib, Fadi
Moran, Dror
Trostianetsky, Guy
Kasten, Yoni
Galun, Meirav
Basri, Ronen
author_facet Khatib, Fadi
Moran, Dror
Trostianetsky, Guy
Kasten, Yoni
Galun, Meirav
Basri, Ronen
contents We introduce GSVisLoc, a visual localization method designed for 3D Gaussian Splatting (3DGS) scene representations. Given a 3DGS model of a scene and a query image, our goal is to estimate the camera's position and orientation. We accomplish this by robustly matching scene features to image features. Scene features are produced by downsampling and encoding the 3D Gaussians while image features are obtained by encoding image patches. Our algorithm proceeds in three steps, starting with coarse matching, then fine matching, and finally by applying pose refinement for an accurate final estimate. Importantly, our method leverages the explicit 3DGS scene representation for visual localization without requiring modifications, retraining, or additional reference images. We evaluate GSVisLoc on both indoor and outdoor scenes, demonstrating competitive localization performance on standard benchmarks while outperforming existing 3DGS-based baselines. Moreover, our approach generalizes effectively to novel scenes without additional training.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18242
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations
Khatib, Fadi
Moran, Dror
Trostianetsky, Guy
Kasten, Yoni
Galun, Meirav
Basri, Ronen
Computer Vision and Pattern Recognition
We introduce GSVisLoc, a visual localization method designed for 3D Gaussian Splatting (3DGS) scene representations. Given a 3DGS model of a scene and a query image, our goal is to estimate the camera's position and orientation. We accomplish this by robustly matching scene features to image features. Scene features are produced by downsampling and encoding the 3D Gaussians while image features are obtained by encoding image patches. Our algorithm proceeds in three steps, starting with coarse matching, then fine matching, and finally by applying pose refinement for an accurate final estimate. Importantly, our method leverages the explicit 3DGS scene representation for visual localization without requiring modifications, retraining, or additional reference images. We evaluate GSVisLoc on both indoor and outdoor scenes, demonstrating competitive localization performance on standard benchmarks while outperforming existing 3DGS-based baselines. Moreover, our approach generalizes effectively to novel scenes without additional training.
title GSVisLoc: Generalizable Visual Localization for Gaussian Splatting Scene Representations
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.18242