search

mihaidusmanu / d2-net

D2-Net: A Trainable CNN for Joint Description and Detection of Local Features
Other
761 stars 163 forks source link

why need this transformation in the extract_feature.py #80

Closed fantuslk closed 3 years ago

fantuslk commented 3 years ago

Hi mihaidusmanu, 捕获 why i,j to u,v?

mihaidusmanu commented 3 years ago

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.