MegaLoc: One Retrieval to Place Them All

Gabriele Berton, Carlo Masone
2/24/2025
cs.CV

Official code: gmberton/MegaLoc (312 stars, MIT, last commit 2026-03-30).

Abstract

Retrieving images from the same location as a given query is an important component of multiple computer vision tasks, like Visual Place Recognition, Landmark Retrieval, Visual Localization, 3D reconstruction, and SLAM. However, existing solutions are built to specifically work for one of these tasks, and are known to fail when the requirements slightly change or when they meet out-of-distribution data. In this paper we combine a variety of existing methods, training techniques, and datasets to train a retrieval model, called MegaLoc, that is performant on multiple tasks. We find that MegaLoc (1) achieves state of the art on a large number of Visual Place Recognition datasets, (2) impressive results on common Landmark Retrieval datasets, and (3) sets a new state of the art for Visual Localization on the LaMAR datasets, where we only changed the retrieval method to the existing localization pipeline. The code for MegaLoc is available at https://github.com/gmberton/MegaLoc

View on arXivView PDF

Code Implementations(1)

gmberton/MegaLocOfficial100%
MIT

An image retrieval model for any localization task

31210PythonFeb 17, 20256 months agoMIT
geolocalizationimage-retrievallocalizationplace-recognitionvisual-geolocalization+2 more

Similar Papers

Multiview Image-Based Localization

87% match2025

TBPos: Dataset for Large-Scale Precision Visual Localization

85% match2023

LoGS: Visual Localization via Gaussian Splatting with Fewer Training Images

85% match2 repos242024

A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features

84% match2025

ProGEO: Generating Prompts through Image-Text Contrastive Learning for Visual Geo-localization

83% match1 repo502024

3DGS-ReLoc: 3D Gaussian Splatting for Map Representation and Visual ReLocalization

83% match2024

Cite this paper

@article{berton2025megaloc,
  title  = {MegaLoc: One Retrieval to Place Them All},
  author = {Gabriele Berton and Carlo Masone},
  year   = {2025},
  eprint = {2502.17237},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.17237v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.17237.svg)](https://codeofpaper.com/paper/2502.17237)

Discussion