mihaidusmanu/d2-net

why need this transformation in the extract_feature.py

fantuslk opened this issue · 1 comments

Hi mihaidusmanu,
捕获
why i,j to u,v?

We output keypoints in COLMAP format which is x, y with x pointing to the right and y pointing down. Please refer to the readme for more details https://github.com/mihaidusmanu/d2-net#feature-extraction. Depending on your specific application, you might want to use a different ordering.