Close, But Not There: Boosting Geographic Distance Sensitivity In Visual Place Recognition

Abstract

Visual Place Recognition (VPR) plays a critical role in many localization and mapping pipelines. It consists of retrieving the closest sample to a query image, in a certain embedding space, from a database of geotagged references. The image embedding is learned to effectively describe a place despite variations in visual appearance, viewpoint, and geometric changes. In this work, we formulate how limitations in the Geographic Distance Sensitivity of current VPR embeddings result in a high probability of incorrectly sorting the top-k retrievals, negatively impacting the recall. In order to address this issue in single-stage VPR, we propose a novel mining strategy, CliqueMining, that selects positive and negative examples by sampling cliques from a graph of visually similar images. Our approach boosts the sensitivity of VPR embeddings at small distance ranges, significantly improving the state of the art on relevant benchmarks. In particular, we raise recall@1 from 75% to 82% in MSLS Cha

Stats

• citations8
• S2 citations—
• github stars41
• HF likes0
• heat score10.40
• arxiv keyizquierdo2024close

Related papers

• Focus On Local: Finding Reliable Discriminative Regions For Visual Place Recognition (2025)10.70
• Multires-netvlad: Augmenting Place Recognition Training With Low-resolution Imagery (2022)16.01
• SAGE: Spatial-visual Adaptive Graph Exploration For Efficient Visual Place Recognition (2025)2.16
• Optimal Transport Aggregation For Visual Place Recognition (2023)20.51
• Data-efficient Large Scale Place Recognition With Graded Similarity Supervision (2023)16.32
• Towards Test-time Efficient Visual Place Recognition Via Asymmetric Query Processing (2025)0.00
• Evaluation Of Visual Place Recognition Methods For Image Pair Retrieval In 3D Vision And Robotics (2026)0.00
• Mutualvpr: A Mutual Learning Framework For Resolving Supervision Inconsistencies Via Adaptive Clustering (2024)0.00