-
Notifications
You must be signed in to change notification settings - Fork 554
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Parameter updating by novel view synthesis #10
Comments
Oh, why do you think the gradients cannot backprop through |
Sorry, now I understand: the gradient is backpropagated to depth and pose through the calculated weights Am I wrong if I think that the optimization works because the baseline between consecutive frames is small? I mean, if the baseline were greater, the optimization wouldn't work, right? Cheers! |
You are right that the gradients for depth and pose are backproped through the w's, and the gradient can only be derived from the four neighboring pixels used in the interpolation, which is why we use a multi-scale loss and depth smoothness loss in the objective to overcome the gradient locality (see Sec. 3.4 of the paper). With multi-scale and smoothness, the system is able to deal with reasonably large baselines. |
Oh, I didn't take that into account. Thank you very much for the explanation and for sharing your code! Cheers! |
Hi @tinghuiz,
The method
_interpolate
in fileutils.py
samples pixels in the source image withtf.gather
, given the indices computed from intrinsics matrices and depth. The gradient oftf.gather
is not computed w.r.t. the indices, so backpropagation does not reach the tensor of the computed depth (or, similarly, the pose). So,How does the network update the depth (pose) parameters? Am I missing something in the analysis?
Cheers.
The text was updated successfully, but these errors were encountered: