To Match or Not to Match: Revisiting Image Matching for Reliable Visual Place Recognition

Davide Sferrazza, Gabriele Berton, Gabriele Trivigno, Carlo Masone
4/8/2025
cs.CV

Official code: FarInHeight/To-Match-or-Not-to-Match (39 stars, MIT, PyTorch, last commit 2025-10-04).

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.

View on arXivView PDF

Code Implementations(1)

FarInHeight/To-Match-or-Not-to-MatchOfficial100%
PyTorchMIT

Official code for "To Match or Not to Match: Revisiting Image Matching for Reliable Visual Place Recognition" CVPR IMW 2025

392PythonApr 16, 20251 years agoMIT
computer-visionimage-matchingimage-retrievalplace-recognitionpytorch+2 more

Similar Papers

Chain-of-Thought Re-ranking for Image Retrieval Tasks

88% match1 repo72025

Global-to-Local or Local-to-Global? Enhancing Image Retrieval with Efficient Local Search and Effective Global Re-ranking

83% match2025

A Review of Image Retrieval Techniques: Data Augmentation and Adversarial Learning Approaches

83% match2024

Patch-wise Retrieval: A Bag of Practical Techniques for Instance-level Matching

83% match1 repo42025

FORB: A Flat Object Retrieval Benchmark for Universal Image Embedding

82% match1 repo132026

ILIAS: Instance-Level Image retrieval At Scale

82% match1 repo372026

Cite this paper

@article{sferrazza2025match,
  title  = {To Match or Not to Match: Revisiting Image Matching for Reliable Visual Place Recognition},
  author = {Davide Sferrazza and Gabriele Berton and Gabriele Trivigno and Carlo Masone},
  year   = {2025},
  eprint = {2504.06116},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2504.06116v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2504.06116.svg)](https://codeofpaper.com/paper/2504.06116)

Discussion