Closed Aniket-Gujarathi closed 3 years ago
In theory you can replace the function warp with your correspondences.
The ids
are used to filter out points / descriptors that do not have correspondences. As you stated, it is simply the row-major index of valid points of the grid.
https://github.com/mihaidusmanu/d2-net/blob/2a4d88fbe84961a3a17c46adb6d16a94b87020c5/lib/loss.py#L70-L72
Hi, Thank you for the clarification.
Hi , I would like to know how can I manually give the correspondences to train the network, instead of giving pose, depth, rgb and intrinsics. It would be much convenient for me train that way in my project.
pos1
andpos2
. But I am not sure ofids
tensor, is it returning the descriptors' index forpos1
in row major order? Could we replace this warping function with our input data.