Giters

mattpoggi / mono-uncertainty

CVPR 2020 - On the uncertainty of self-supervised monocular depth estimation

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

some questions about my implementation

Bowwowlol opened this issue · comments

commented

Hi, @mattpoggi,
Thanks for your excellent work!!
I have some questions about my implementation.

  1. In the depth decoder (S), it is output 4 scale disparity and uncertainty, I would like to know that have you calculated all scale outputs when you implemented eq.14?
    image

  2. If my uncertainty has some negative values, Should I limit it to>0?

commented

Hi @Bowwowlol,

  1. depth and uncertainty at each scale are upsampled to full resolution when computing the loss
  2. if you assume your output uncertainty is u=log(uncertainty), you should be fine (then replace sigma with exp(u) in the loss function)
commented

Hi, @mattpoggi,
Thank you for the quick reply!!
I really appreciate your help in resolving problems, That is very helpful to me.
Good luck!!