Seongwon Lee

@andrefaraujo and @feymanpriv I uploaded the reproduced ROxford/RParis results with R101-DOLG model including the query cropping process in [here](https://github.com/feymanpriv/DOLG-paddle/issues/3). I hope this helps.

We wanted to upload the material before the conference, but we couldn't upload it due to time constraints. It will be uploaded after the conference.

Hi. Thanks for the answer. I understand that corner points do not look good on point cloud because of horizontally located markers. But I think some problem occurs with my...

@almazan Thanks for the great code and explanation! I am eagerly looking for gldv2 trained weights and results. What plan do you have for these results? I hope to see...

> Thanks @sungonce for the experiments and for looping me in here! > > Indeed as expected the numbers go down in the 1M evals. The numbers still look quite...