Skip to content
This repository has been archived by the owner on Jul 23, 2024. It is now read-only.

Normal estimation using gradient of density #44

Open
mra-h opened this issue Aug 4, 2023 · 0 comments
Open

Normal estimation using gradient of density #44

mra-h opened this issue Aug 4, 2023 · 0 comments

Comments

@mra-h
Copy link

mra-h commented Aug 4, 2023

Hello,

Thank you so much for this implementation of ref nerf!

I have a question regarding on the gradient of the density to compute the normals. Why is raw_density.sum() used as outputs in torch.autograd as shown here.

Is it different than calculating the gradient as
torch.autograd.grad(raw_density, means, grad_outputs=torch.ones_like(raw_density), retain_graph=True). ?

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant