Evaluation Of Visual Place Recognition Methods For Image Pair Retrieval In 3D Vision And Robotics

Abstract

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

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhaitz2026evaluation

Related papers

• Embodiedplace: Learning Mixture-of-features With Embodied Constraints For Visual Place Recognition (2025)0.00
• Range And Bird's Eye View Fused Cross-modal Visual Place Recognition (2025)0.00
• Mixvpr: Feature Mixing For Visual Place Recognition (2023)22.68
• Lavpr: Benchmarking Language And Vision For Place Recognition (2026)2.35
• Focus On Local: Finding Reliable Discriminative Regions For Visual Place Recognition (2025)10.70
• To Match Or Not To Match: Revisiting Image Matching For Reliable Visual Place Recognition (2025)5.46
• Scicevpr: Stable Cross-image Correlation Enhanced Model For Visual Place Recognition (2025)4.06
• Unipr-3d: Towards Universal Visual Place Recognition With Visual Geometry Grounded Transformer (2025)2.95