About the depth volume predicted by the mono depth
EchoTHChen opened this issue · 1 comments
EchoTHChen commented
I have a question. mu + k*sigma
might be negative. The depth volume constructed by negative depth might bring some errors to the training results. How do the depth volume work and keep positive?
baegwangbin commented
Hi, thanks for your interest.
Yes, this can happen. But in practice, the estimated 'mu' is positive (usually > 1m) and the scale of 'sigma' is significantly smaller than that of 'mu' - so 'mu + k*sigma' stays positive.