Loss Function on Paper

[sami-automatic]

Thank you for sharing all of your code, this is an amazing contribution to depth society.

I would like to ask why do you add 15% of the mse instead of substracting the 85% of mse in your loss function below? https://github.com/shariqfarooq123/AdaBins/blob/2fb686a66a304f0a719bc53d77412460af97fd61/loss.py#L24

I was curious since your paper refers to a substraction as follows:

Thank you for your time

[shariqfarooq123]

Thank you for your kind words.

The two formulations are equivalent by definition of variance:

[sami-automatic]

Thank you for your answer