Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kalantidis, Yannis, Sarıyıldız, Mert Bülent, Rezende, Rafael S., Weinzaepfel, Philippe, Larlus, Diane, Csurka, Gabriela
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914679077470208
author Kalantidis, Yannis
Sarıyıldız, Mert Bülent
Rezende, Rafael S.
Weinzaepfel, Philippe
Larlus, Diane
Csurka, Gabriela
author_facet Kalantidis, Yannis
Sarıyıldız, Mert Bülent
Rezende, Rafael S.
Weinzaepfel, Philippe
Larlus, Diane
Csurka, Gabriela
contents State-of-the-art visual localization approaches generally rely on a first image retrieval step whose role is crucial. Yet, retrieval often struggles when facing varying conditions, due to e.g. weather or time of day, with dramatic consequences on the visual localization accuracy. In this paper, we improve this retrieval step and tailor it to the final localization task. Among the several changes we advocate for, we propose to synthesize variants of the training set images, obtained from generative text-to-image models, in order to automatically expand the training set towards a number of nameable variations that particularly hurt visual localization. After expanding the training set, we propose a training approach that leverages the specificities and the underlying geometry of this mix of real and synthetic images. We experimentally show that those changes translate into large improvements for the most challenging visual localization datasets. Project page: https://europe.naverlabs.com/ret4loc
format Preprint
id arxiv_https___arxiv_org_abs_2402_09237
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency
Kalantidis, Yannis
Sarıyıldız, Mert Bülent
Rezende, Rafael S.
Weinzaepfel, Philippe
Larlus, Diane
Csurka, Gabriela
Computer Vision and Pattern Recognition
State-of-the-art visual localization approaches generally rely on a first image retrieval step whose role is crucial. Yet, retrieval often struggles when facing varying conditions, due to e.g. weather or time of day, with dramatic consequences on the visual localization accuracy. In this paper, we improve this retrieval step and tailor it to the final localization task. Among the several changes we advocate for, we propose to synthesize variants of the training set images, obtained from generative text-to-image models, in order to automatically expand the training set towards a number of nameable variations that particularly hurt visual localization. After expanding the training set, we propose a training approach that leverages the specificities and the underlying geometry of this mix of real and synthetic images. We experimentally show that those changes translate into large improvements for the most challenging visual localization datasets. Project page: https://europe.naverlabs.com/ret4loc
title Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.09237