Clarifications on training pipeline about mannequinchallenge HOT 2 CLOSED

Hi,
(1) Yes. I have fixed it in https://www.cs.cornell.edu/~zl548/images/mannequin_depth_cvpr2019_supp_doc.pdf
(2) The centering will not change the log difference between each pair of depth. Since SfM model could have very arbitrary scale, this trick just make sure the depth range is reasonable. If you want to convert your prediction back to original SfM model, you have to use either SfM point or MVS point to scale them back.
(3) If you look at 2.4 in our supplementary material: https://www.cs.cornell.edu/~zl548/images/mannequin_depth_cvpr2019_supp_doc.pdf. I showed the algebra trick to make the all-pairs O(N^2) computed in linear time (and in closed form). So you don't need to sample the pixels.

from mannequinchallenge.

Thanks for the quick reply

from mannequinchallenge.