Johan Edstedt · Georg Bökman · Mårten Wadenbäck · Michael Felsberg
The DeDoDe detector learns to detect 3D consistent repeatable keypoints, which the DeDoDe descriptor learns to match. The result is a powerful decoupled local feature matcher.
We experimentally find that DeDoDe significantly closes the performance gap between detector + descriptor models and fully-fledged matchers. The potential of DeDoDe is not limited to local feature matching, in fact we find that we can improve state-of-the-art matchers by incorporating DeDoDe keypoints.
Below we show how DeDoDe can be run, you can also check out the demos
from DeDoDe import dedode_detector_L, dedode_descriptor_B, dedode_descriptor_G
from DeDoDe.matchers.dual_softmax_matcher import DualSoftMaxMatcher
detector = dedode_detector_L(weights = torch.load("dedode_detector_L.pth"))
# Choose either a smaller descriptor,
descriptor = dedode_descriptor_B(weights = torch.load("dedode_descriptor_B.pth"))
# Or a larger one
descriptor = dedode_descriptor_G(weights = torch.load("dedode_descriptor_G.pth"),
dinov2_weights = None) # You can manually load dinov2 weights, or we'll pull from facebook
matcher = DualSoftMaxMatcher()
im_A_path = "assets/im_A.jpg"
im_B_path = "assets/im_B.jpg"
im_A = Image.open(im_A_path)
im_B = Image.open(im_B_path)
W_A, H_A = im_A.size
W_B, H_B = im_B.size
detections_A = detector.detect_from_path(im_A_path, num_keypoints = 10_000)
keypoints_A, P_A = detections_A["keypoints"], detections_A["confidence"]
detections_B = detector.detect_from_path(im_B_path, num_keypoints = 10_000)
keypoints_B, P_B = detections_B["keypoints"], detections_B["confidence"]
description_A = descriptor.describe_keypoints_from_path(im_A_path, keypoints_A)["descriptions"]
description_B = descriptor.describe_keypoints_from_path(im_B_path, keypoints_B)["descriptions"]
matches_A, matches_B, batch_ids = matcher.match(keypoints_A, description_A,
keypoints_B, description_B,
P_A = P_A, P_B = P_B,
normalize = True, inv_temp=20, threshold = 0.1)#Increasing threshold -> fewer matches, fewer outliers
matches_A, matches_B = matcher.to_pixel_coords(matches_A, matches_B, H_A, W_A, H_B, W_B)
Right now you can find them here: https://github.com/Parskatt/DeDoDe/releases/tag/dedode_pretrained_models Probably we'll add some autoloading in the near future.
- fabio-sim/DeDoDe-ONNX-TensorRT: Deploy DeDoDe with ONNX and TensorRT 🚀
- Image Matching WebUI: a web GUI to easily compare different matchers, including DeDoDe 🤗
All code/models except DINOv2 (descriptor-G), are MIT license (do whatever you want). DINOv2 has a non-commercial license (see LICENSE_DINOv2).
@article{edstedt2023dedode,
title={{DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching}},
author={Johan Edstedt and Georg Bökman and Mårten Wadenbäck and Michael Felsberg},
year={2023},
eprint={2308.08479},
archivePrefix={arXiv},
primaryClass={cs.CV}
}