Closed jahaniam closed 6 years ago
Hi,
The network outputs disp
through a sigmoid, which is then turned into a depth through:
min_disp = 1 / max_depth
max_disp = 1 / min_depth
scaled_disp = min_disp + (max_disp - min_disp) * disp
depth = 1 / scaled_disp
Where we used max_depth = 100 and min_depth = 0.1
I hope this helps!
@a-jahani The implementation is now public at https://github.com/nianticlabs/monodepth2
I was wondering if your network output for "self-supervised Stereo Training" is disparity or inverse depth?
"With known focal length and camera baseline the predicted disparity map, i.e. the inverse depth map, can then be converted into scaled metric depth"
Thanks