About disp to depth

[GANWANSHUI]

Hi， Thanks a lot for the nice work!

I have a basic question about the disp to depth as follows:

def disp_to_depth(disp, min_depth, max_depth): """Convert network's sigmoid output into depth prediction The formula for this conversion is given in the 'additional considerations' section of the paper. """ min_disp = 1 / max_depth max_disp = 1 / min_depth scaled_disp = min_disp + (max_disp - min_disp) * disp # 0~1 0.1~10 depth = 1 / scaled_disp # 0.1~10 return scaled_disp, depth

May I ask the reason that doing such an operation for depth rather than disp * max_depth? Thanks a lot for your help!

[weiyithu]

This operation is from monodepth2. Actually, I have tried directly * max_depth and they have comarable performances.

[GANWANSHUI]

Hi， I have tried to use this disp* max_depth setting, but still does not work. May I have your Wechat for the detail about this setting? Thank you!

[weiyithu]

Here is my Wechat 18600500891.