To Match Or Not To Match: Revisiting Image Matching For Reliable Visual Place Recognition

Abstract

Visual Place Recognition (VPR) is a critical task in computer vision, traditionally enhanced by re-ranking retrieval results with image matching. However, recent advancements in VPR methods have significantly improved performance, challenging the necessity of re-ranking. In this work, we show that modern retrieval systems often reach a point where re-ranking can degrade results, as current VPR datasets are largely saturated. We propose using image matching as a verification step to assess retrieval confidence, demonstrating that inlier counts can reliably predict when re-ranking is beneficial. Our findings shift the paradigm of retrieval pipelines, offering insights for more robust and adaptive VPR systems. The code is available at https://github.com/FarInHeight/To-Match-or-Not-to-Match.

Stats

• citations1
• S2 citations—
• github stars39
• HF likes0
• heat score5.46
• arxiv keysferrazza2025to

Code

• FarInHeight/To-Match-or-Not-to-Match—

Related papers

• Evaluation Of Visual Place Recognition Methods For Image Pair Retrieval In 3D Vision And Robotics (2026)0.00
• On The Estimation Of Image-matching Uncertainty In Visual Place Recognition (2024)7.50
• Focus On Local: Finding Reliable Discriminative Regions For Visual Place Recognition (2025)10.70
• 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
• Attention-aware Age-agnostic Visual Place Recognition (2019)8.82
• Close, But Not There: Boosting Geographic Distance Sensitivity In Visual Place Recognition (2024)10.40
• Lavpr: Benchmarking Language And Vision For Place Recognition (2026)2.35