How fast can image matching be?

• FastMatch
  • Table of Contents
  • 1. Introduction
  • 2. Installation
    • 2.1. Clone the repository
    • 2.2. Install dependencies
  • 3. Usage
  • 4. Results
    • 4.1 Time Comparison
    • 4.2 Video Matching
  • 5. Thanks To
  • 6. License

This repository aims to combine the fastest feature extraction and matching methods, i.e. XFeat and LightGlue, and evaluate their performance on laptop and service devices.

git clone https://github.com/LuoXubo/FastMatch.git

conda create -n fastmatch python=3.8 -y
conda activate fastmatch
pip install -r requirements.txt

See demo.ipynb for a quick start.

• Test device: Ubuntu 20.04, RTX 3090 Ti
• Test image size: 800x600

Notice: These methods are tested in a jupyter notebook, so the actual runing speed may be faster than the results.

Test on Orin Nano:

• Test device: Nvidia Jetson Orin Nano
• Test image size: 4000x4000

• Test device: Ubuntu 20.04, RTX 3090 Ti
• Test video size: 1280x720, 30fps, shot by iPhone 13
• Test video length: 12s

XFeat + mnn

SuperPoint + LightGlue

Efficient LoFTR

XFeat + LighterGlue

Usage:

python video_matching.py --ref=assets/groot/groot.jpg --tgt=assets/groot/groot.mp4 --method=sp+lg --save_path=assets/groot/groot_sp+lg.mp4

• XFeat
• LightGlue

This project is licensed under the MIT License - see the LICENSE.md file for details.