Open JonathanLehner opened 2 years ago
@JonathanLehner Hi, The ray sampling and integrated position encoding in mip-nerf seems to require substantial changes to the current ray sampling implementation. How to combine it with hashgrid encoding is also a problem. For the ray contraction in mip-nerf 360, we may be able to implement a similar approach using the L-inf norm instead of the L2 norm (so the sphere becomes a box to suit the hashgrid encoding) like in DVGO.
The ray sampling and integrated position encoding in mip-nerf seems to require substantial changes to the current ray sampling implementation.
Combining the mip-nerf sampling strategy should lead to major slowdown of training and inference speed, right ?
Also I'm very curious on how the "distortion loss" will perform with ngp.
Correct me if I'm mistaken.
What about Ref-NeRF? it might be easier
What do you think about Mip-NeRF and Mip-NeRF 360? Do you have ideas how to integrate them?