-
Hello!! Thanks for your share. And I want to run bash download_cache.sh. But the link to "https://dsmn.ml/files/d2-net/hpatches-sequences-cache.tar.gz" seems broken. Can you share the new link please?
-
Hi!
I was reading about the issue #117 for the homography and was basing my inplementation on yours. I am not getting the right outputs. Forexample,
![image](https://github.com/rpautrat/SuperPoi…
-
Hi,
This is very nice implementation and it is very useful. However i have a question, is there anyway we can verify the correctness of homography matrix?
Thanks,
Veeru.
-
Thank you for your excellent work,Nearest neighbor matching is generally used in hpatches datasets, and I wonder if the network can match via Superglue or Lightglue
-
Hi, if I get a .r2d2 extension (including descriptors.npy, imsize.npy, keypoints.npy and scores.npy) after running the extract.py, how can I evaluate it on Hpatches and visualize the results using d2-…
-
Hi there
In the Readme file there are details about some of the pretrained models. There is a column about the network size (# of parameters).
| model name | model size(#weights)| nu…
-
Hello,author, I would like to inquire why feature extraction is often performed on single-channel gray images. What are the advantages of this approach and is it possible to use three-channel color i…
-
Could you please share the code about how to evaluate the model on the HPatches datasets?
-
Hello and thank you very much for this work. I tested the effect of ORB feature enhancement before and after using the trained model in your open source project, the test results are as follows, but i…
-
Hello, thank you for sharing your excellent work. Let me ask the code about HPatches-Sequences-Matching-Benchmark.
After feature extraction,i want to use HPatches-Sequences-Matching-Benchmark to anal…