-
Hi,ufukefe!
Thank you so much for your beautiful work!
I want to use your algorithm for multi-modal image matching (infrared and visible images).May I ask what modifications I need to make.
Thanks!
-
In the instructions mentioned for running evaluations on NOCS, what is the directory of [PATH TO THE RUNNING OUTPUTS]?
Also while running predictions on **NOCS**, I followed #15 's instructions and …
-
Hi @rpautrat, I'm trying to implement SuperPoint paper in PyTorch and your repository is helping me a lot, thank you. I'm having some difficulties training the descriptors in SuperPoint.
The detectio…
-
Hi,
I computed repeatability score of [pre-trained SuperPoint network](https://github.com/MagicLeapResearch/SuperPointPretrainedNetwork) using the repeatability code provided at https://github.com/rp…
-
Some users keep claiming they have "invalid IL code" errors, but I was unable to know what is going on. Running out of options, I hypothesized that another mod that I was not aware of was also modifyi…
-
Hello,
I tried to estimate a homography on HPatches dataset using pretrained model sp_v6. I got quite small correctnesses. Could you clarify, if I need to finetune a model before estimation?
-
Sorry to bother you,
I have evaluated the pertrained models on HPatches and RDNIM datasets already.
If I want to compare the performance of SuperPoint on these datasets, how can I do it? Could you …
-
Hello, When I am running your evaluation notebook in notebooks/hpatches_evaluation.ipynb, I get the error: No such file or directory: '/home/victor/LISRD/Documents/datasets/Hpatches_sequences/i_nijmeg…
-
Hi! In the Suppl. Section A, says
> we use a threshold ε to determine if a returned point location x is correct relative to a set of K ground-truth corners {ˆx1, . . . , ˆxK}.
Is the ground tru…
-
Hi @PruneTruong ,
Thanks for the great work! I found that DGC-Net can only accept 240x240 image but there are evaluation results of DGC-Net based on the original size of hpatches. Which strategy did …