kishore-greddy

NaN in loss while training the log model

16

Hey @mattpoggi , I was trying to train the log model. I made necessary changes to the decoder to include the additional channel. When I start training, the intial loss...

Evaluation of relative depth

1

Hello, Thanks for your amazing work. I have a question regarding evaluating relative depth. I see from your paper that the errors are as below:  How to reproduce these...

Sharpness of depthmaps of metric model is significantly lower than relative depth model

2

Hello @LiheYoung, I was experimenting with both the relative depth model as well as the metric depth model and it seems like the relative depth model produces much sharper depth...