Megaloc: One Retrieval To Place Them All

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

Stats

• citations3
• S2 citations—
• github stars216
• HF likes0
• heat score9.19
• arxiv keyberton2025megaloc

Code

• gmberton/MegaLoc—

Related papers

• Investigating The Role Of Image Retrieval For Visual Localization -- An Exhaustive Benchmark (2022)16.58
• Benchmarking Image Retrieval For Visual Localization (2020)17.78
• Img2loc: Revisiting Image Geolocalization Using Multi-modality Foundation Models And Image-based Retrieval-augmented Generation (2024)9.23
• Are Local Features All You Need For Cross-domain Visual Place Recognition? (2023)13.80
• Uniloc: Towards Universal Place Recognition Using Any Single Modality (2024)0.00
• Why-so-deep: Towards Boosting Previously Trained Models For Visual Place Recognition (2022)7.81
• Evaluation Of Visual Place Recognition Methods For Image Pair Retrieval In 3D Vision And Robotics (2026)0.00
• VIGOR: Cross-view Image Geo-localization Beyond One-to-one Retrieval (2020)21.49