search

google-research / multinerf

A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF
Apache License 2.0
3.58k stars 339 forks source link

implementation of orientation loss in ref-nerf #42

Closed kwea123 closed 1 year ago

kwea123 commented 1 year ago

Why is here min(0, n_dot_v)? Shouldn't it be max as in the paper?

https://github.com/google-research/multinerf/blob/b02228160d3179300c7d499dca28cb9ca3677f32/internal/train_utils.py#L167

kwea123 commented 1 year ago

Sorry I misunderstood, v is -d so the formula is correct.