MegaLoc: One Retrieval to Place Them All

TL;DR

MegaLoc is a unified image retrieval model that performs well across multiple vision tasks like place recognition, landmark retrieval, and localization, surpassing existing methods on several benchmarks.

Contribution

The paper introduces MegaLoc, a versatile retrieval model trained with combined techniques and datasets, achieving state-of-the-art results across multiple vision tasks.

Findings

State-of-the-art on numerous Visual Place Recognition datasets.

Impressive performance on Landmark Retrieval datasets.

New best results for Visual Localization on LaMAR datasets.

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