Skip to content

Conversation

Phil26AT
Copy link
Collaborator

@Phil26AT Phil26AT commented Jul 5, 2025

Simple download script to download the weights of GIM: Learning Generalizable Image Matcher From Internet Videos by Xuelun Shen (@xuelunshen) et al. to LightGlue.

They are directly compatible with LightGlue and SuperPoint features:

from lightglue import LightGlue, SuperPoint

# SuperPoint+LightGlue
extractor = SuperPoint(max_num_keypoints=2048).eval().cuda()  # load the extractor
matcher = LightGlue(features='gim_superpoint').eval().cuda()  # load the matcher

...

Project page: https://xuelunshen.com/gim/
Code: https://github.com/xuelunshen/gim
Paper: https://arxiv.org/abs/2402.11095
Video: https://www.youtube.com/watch?v=FU_MJLD8LeY/
License: MIT

@inproceedings{
xuelun2024gim,
title={GIM: Learning Generalizable Image Matcher From Internet Videos},
author={Xuelun Shen and Zhipeng Cai and Wei Yin and Matthias Müller and Zijun Li and Kaixuan Wang and Xiaozhi Chen and Cheng Wang},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024}
}

@Phil26AT Phil26AT requested a review from sarlinpe July 5, 2025 16:49
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant