Salvato in:
Dettagli Bibliografici
Autori principali: Haitz, Dennis, Shetty, Athradi Shritish, Weinmann, Michael, Ulrich, Markus
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.13917
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915862857908224
author Haitz, Dennis
Shetty, Athradi Shritish
Weinmann, Michael
Ulrich, Markus
author_facet Haitz, Dennis
Shetty, Athradi Shritish
Weinmann, Michael
Ulrich, Markus
contents Visual Place Recognition (VPR) is a core component in computer vision, typically formulated as an image retrieval task for localization, mapping, and navigation. In this work, we instead study VPR as an image pair retrieval front-end for registration pipelines, where the goal is to find top-matching image pairs between two disjoint image sets for downstream tasks such as scene registration, SLAM, and Structure-from-Motion. We comparatively evaluate state-of-the-art VPR families - NetVLAD-style baselines, classification-based global descriptors (CosPlace, EigenPlaces), feature-mixing (MixVPR), and foundation-model-driven methods (AnyLoc, SALAD, MegaLoc) - on three challenging datasets: object-centric outdoor scenes (Tanks and Temples), indoor RGB-D scans (ScanNet-GS), and autonomous-driving sequences (KITTI). We show that modern global descriptor approaches are increasingly suitable as off-the-shelf image pair retrieval modules in challenging scenarios including perceptual aliasing and incomplete sequences, while exhibiting clear, domain-dependent strengths and weaknesses that are critical when choosing VPR components for robust mapping and registration.
format Preprint
id arxiv_https___arxiv_org_abs_2603_13917
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Evaluation of Visual Place Recognition Methods for Image Pair Retrieval in 3D Vision and Robotics
Haitz, Dennis
Shetty, Athradi Shritish
Weinmann, Michael
Ulrich, Markus
Computer Vision and Pattern Recognition
Visual Place Recognition (VPR) is a core component in computer vision, typically formulated as an image retrieval task for localization, mapping, and navigation. In this work, we instead study VPR as an image pair retrieval front-end for registration pipelines, where the goal is to find top-matching image pairs between two disjoint image sets for downstream tasks such as scene registration, SLAM, and Structure-from-Motion. We comparatively evaluate state-of-the-art VPR families - NetVLAD-style baselines, classification-based global descriptors (CosPlace, EigenPlaces), feature-mixing (MixVPR), and foundation-model-driven methods (AnyLoc, SALAD, MegaLoc) - on three challenging datasets: object-centric outdoor scenes (Tanks and Temples), indoor RGB-D scans (ScanNet-GS), and autonomous-driving sequences (KITTI). We show that modern global descriptor approaches are increasingly suitable as off-the-shelf image pair retrieval modules in challenging scenarios including perceptual aliasing and incomplete sequences, while exhibiting clear, domain-dependent strengths and weaknesses that are critical when choosing VPR components for robust mapping and registration.
title Evaluation of Visual Place Recognition Methods for Image Pair Retrieval in 3D Vision and Robotics
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.13917