gmberton/VPR-methods-evaluation

Wrapper for 10+ VPR models. Use any SOTA VPR model just by changing one parameter

48
/ 100
Emerging

This tool helps researchers and engineers quickly evaluate different Visual Place Recognition (VPR) models for tasks like robot localization or autonomous vehicle navigation. You provide collections of images from different locations, and it outputs visual predictions of where each query image is located within the database, along with performance metrics. It's designed for anyone working with robot navigation or visual localization who needs to compare how well various VPR techniques perform on their specific image datasets.

181 stars.

Use this if you need to compare the performance of multiple state-of-the-art Visual Place Recognition (VPR) models on your own image datasets to determine the best approach for a specific localization task.

Not ideal if you need to train new VPR models from scratch or perform fine-tuning, as this tool is focused on evaluating existing, pre-trained models.

robot-localization visual-navigation place-recognition computer-vision robotics-research
No License No Package No Dependents
Maintenance 13 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

181

Forks

25

Language

Python

License

Last pushed

Mar 15, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/gmberton/VPR-methods-evaluation"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.