search

dunbar12138 / DSNeRF

Code release for DS-NeRF (Depth-supervised Neural Radiance Fields)
https://www.cs.cmu.edu/~dsnerf/
MIT License
759 stars 129 forks source link

Potential view inconsistency in depth loss #31

Closed NagabhushanSN95 closed 2 years ago

NagabhushanSN95 commented 2 years ago

Hi,

I noticed that you compute depth in input views in https://github.com/dunbar12138/DSNeRF/blob/main/load_llff.py#L371 but the depth given by NeRF model is in cannonical view https://github.com/dunbar12138/DSNeRF/blob/main/run_nerf_helpers.py#L377

Shouldn't both the depths be brought to same view before computing depth loss? Please let me know if I missed something

dunbar12138 commented 2 years ago

The transformation between different cameras is just rigid transformation, which conserves the length.

NagabhushanSN95 commented 2 years ago

Oh okay. Thanks! Closing the issue