license: mit tags: - image-matching - computer-vision - feature-matching library_name: image-matching-models
Steerers
Rotation invariant keypoint matching model. Uses the DeDoDe keypoint detector.
Usage
from imm import get_matcher
matcher = get_matcher("patch2pix", device=device)
result = matcher(img0, img1)
# result.keys() = ["num_inliers", "H", "all_kpts0", "all_kpts1", "all_desc0", "all_desc1", "matched_kpts0", "matched_kpts1", "inlier_kpts0", "inlier_kpts1"]
Links
- Downloads last month
- 28
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support