aruba01

The feasibility of outputs keypoint and descriptor

1

I am doing some work on visual localization. I think that this task needs tailored keypoint and descriptor and CAPS can be seen as tailored. As Superpoint output keypoint and...

A curious phenomenon in image retrieval

3

I do image retrieval task with `--use_geometric_verification` on the code `perform_retrieval.py` in `delg` folder. To compare different local feature, I tried to replace the local feature of delg with Superpoint....

In my understanding, the paper contains two kinds of image-level similarity, one is measured by the global feature, another is measured by the local feature with ASMK. In some research,...

Thanks for your great work! Could you release the jupyter notebook of MovieLen Tutorial?

Thanks for your great work! I try to train the model on my pc but report cuda out of memory. My GPU is 3060Ti with 8GB memory.