guipotje

Hello @gs-ren, thank you for the interest in our work. We plan to release the applications with the code of an upcoming paper, which should be available in the near...

Hello @gs-ren Yes, sorry for the delay! We released a new method which has a non-rigid tracking demo which you can easily test on Colab (see the gif in the...

Hello @slam-nerf , thank you for the interest in our work! As mentioned in #2 , we plan to release the applications with the code of an upcoming paper, which...

Hello Dmytro, Yes, we are very interested in contributing to Kornia! I will check Kornia's PR guidelines and will start the process of adapting the code of this repo. I...

> I think that the most reasonable would be to inherit from [kornia.feature.LAFDescriptor](https://github.com/kornia/kornia/blob/master/kornia/feature/integrated.py#L61) and put there the deformation-aware patch extraction and description. Sounds nice @ducha-aiki, thank you for the tips....

Hello @adamzenith, thank you for the interest in our work! I believe our architecture is fully compatible with their training pipeline. With minor adjustments, it should be possible to train...

Closing the issue. If you need further clarifications, feel free to re-open it!

Hello @IamShubhamGupto and @acai66, thank you so much for your contributions! I notice that both of you are providing an ONNX export, and it probably doesn't make sense to merge...

> > My PR is aimed at improving the convenience and compatibility of deployment, especially in environments without PyTorch. I've uploaded an example of using the ONNX Runtime Python API,...

Hi @acai66 @IamShubhamGupto , Thank you very much for providing the ONNX examples in both C++ and Python. They look amazing and incredibly useful! Are you still waiting for @IamShubhamGupto...