I read a paper where δ < 1.25, δ < 1.25², δ 1.25³ are given.
Since I do not really know for what they stand for …
My question would be:
- For what exactly do the values stand for?
- Why do we want to get/compair those values?
- How to get those values?
Thanks a lot for your help!
I believe this metric is used in depth estimation use cases comparing the amount of output pixels with a small, medium, and large difference from their ground truth value.
However, I don’t know how these values were defined.
I additionally found this one:
But I still can’t figure it out, what it means.