zhangyp15 / MonoFlex

Released code for Objects are Different: Flexible Monocular 3D Object Detection, CVPR21
MIT License
215 stars 40 forks source link

Depth Uncertainty leading to negative loss #38

Open AlexanderSing opened 2 years ago

AlexanderSing commented 2 years ago

Hey everyone, first of all thank you for your amazing work! I have a question reagarding the depth uncertainty: If I'm not mistaken using the depth uncertainty can lead to negative loss values, if the loss is low and the uncertainty is a large negative value e.g.:

If the depth loss is 0.0001 and the uncertainty (log(sigma^2)) is -10 this would lead to a loss of ~-7.8.

0.0001*exp(10) - 10 = 7.79...

Is this desired behaviour? If yes, could you explain the reasoning? If no, how does one prevent this? And also if I understood something wrong help is appreciated.

Best regards