Question about using monocular camera images dataset

TRI-ML / packnet-sfm

TRI-ML Monocular Depth Estimation Repository

https://tri-ml.github.io/packnet-sfm/

MIT License

1.24k stars 243 forks source link

Question about using monocular camera images dataset #56

Closed soheilAppear closed 4 years ago

soheilAppear commented 4 years ago

I was checking the Kitti dataset that you used and noticed there are Right and Left side camera images for the training process. Is it possible for us to use only one camera for the training process with PackNet? (I mean not using left and right camera images)

Thanks, Soheil

soheilAppear commented 4 years ago

I mean do we need a pair of cameras for left and right images at the same time? or one camera is fine for the training process?

VitorGuizilini-TRI commented 4 years ago

One camera is completely fine, that is how we train all of our models. We support KITTI right and left image loading for completeness, and also because we can use them independently as data augmentation.