Matteo Poggi

Hi @kishore-greddy 1-2. the uncertainty is usually unbounded but might lead your network to instability. As you noticed in your "EDIT", if you model log-uncertainty you should fix the problem....

I made some experiments by bounding the uncertainty in 0-1 with a sigmoid layer and adding the log term in the loss function, as you mentioned. The same strategy is...

That's quite weird, I actually never had a problem with gradients... Does this occur at any training? Does this occur even if you use the sigmoid trick? Anyway, before the...

You properly upsampled the uncertainty to the proper resolution scale, right? I can dig more into this after the CVPR rebuttal occurring this week... Just a few questions: 1) are...

Everything looks good. I'll try to give a look at it next week

I launched a single train and it ended without issues. I'll try a few more times

Hi, sorry for late. Are you trying to estimate log uncertainty as we mentioned in the previous comments? Among them, we also mentioned using a sigmoid in place of modeling...

Sorry for the very late reply. How do you save depth maps from the teacher? Do you save scaled depths, inverse depth or anything else?

Hi, I never tried, because the negative loss never gave issues in my experiments. You can use sigmoids over the outputs, but I think your solution should work as well.

Hi @Prakadeeswaran05 that's weird, the weights should be compatible with monodepth training scripts. You can have a look here to selectively restore only a portion of the variables from the...