Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,31 +9,6 @@ short_description: A unified API wrapping 50+ image matching models
|
|
| 9 |
license: bsd
|
| 10 |
---
|
| 11 |
|
| 12 |
-
#
|
| 13 |
-
IMM is a unified interface that wraps 37+ image matching models, making it easy to apply the models to a downstream task or eval with minimal boilerplate. We provide a simple API for deploying keypoint, semi dense, and dense image matching models on image pairs.
|
| 14 |
|
| 15 |
-
|
| 16 |
-
[](https://colab.research.google.com/github/alexstoken/image-matching-models/blob/main/demo.ipynb)
|
| 17 |
-
#### Install
|
| 18 |
-
```
|
| 19 |
-
pip install imm
|
| 20 |
-
```
|
| 21 |
-
|
| 22 |
-
#### Usage Example:
|
| 23 |
-
```
|
| 24 |
-
from imm import get_matcher
|
| 25 |
-
from imm.viz import plot_matches
|
| 26 |
-
|
| 27 |
-
device = 'cuda' # 'cpu'
|
| 28 |
-
matcher = get_matcher('my-fav-matcher', device=device) # Choose any of our ~37+ matchers listed below
|
| 29 |
-
img_size = 512 # optional
|
| 30 |
-
|
| 31 |
-
img0 = matcher.load_image('imm/assets/example_pairs/outdoor/montmartre_close.jpg', resize=img_size)
|
| 32 |
-
img1 = matcher.load_image('imm/assets/example_pairs/outdoor/montmartre_far.jpg', resize=img_size)
|
| 33 |
-
|
| 34 |
-
result = matcher(img0, img1)
|
| 35 |
-
# result.keys() = ['num_inliers', 'H', 'all_kpts0', 'all_kpts1', 'all_desc0', 'all_desc1', 'matched_kpts0', 'matched_kpts1', 'inlier_kpts0', 'inlier_kpts1']
|
| 36 |
-
plot_matches(img0, img1, result, save_path='plot_matches.png')
|
| 37 |
-
```
|
| 38 |
-
|
| 39 |
-
See our [github repo](https://github.com/alexstoken/image-matching-models) for a full list of supported models and example scripts and notebooks.
|
|
|
|
| 9 |
license: bsd
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# We have moved!
|
|
|
|
| 13 |
|
| 14 |
+
This organization has moved to [**vismatch**](https://huggingface.co/vismatch). This org will be deleted in a few weeks.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|