some questions about my implementation
Bowwowlol opened this issue · comments
Hi, @mattpoggi,
Thanks for your excellent work!!
I have some questions about my implementation.
Hi @Bowwowlol,
- depth and uncertainty at each scale are upsampled to full resolution when computing the loss
- if you assume your output uncertainty is u=log(uncertainty), you should be fine (then replace sigma with exp(u) in the loss function)
Hi, @mattpoggi,
Thank you for the quick reply!!
I really appreciate your help in resolving problems, That is very helpful to me.
Good luck!!